Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Inworld AI / TTS-2

Realtime TTS-2

Realtime speech synthesis with multilingual voices, persistent delivery instructions, optional professional voice tuning and separate long-form async and discounted batch APIs.

availableClosed weightsText-to-speech
Official documentation (opens in a new tab)Reviewed 13 Oct 2026
17 of 26 specification fields collected
Text input limitUnary 2,000 UTF-16 code units; HTTP stream 4,000; WebSocket 2,000 per sendText messageSee specification notes below
Languages470 listedFull language list in specifications
Input billingSee ratesInworld API
Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum output
Not collected
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Batch processing
SupportedSource for Batch processing (opens in a new tab)

Native batch synthesis is Preview and accepts inworld-tts-2 only.

Fine-tuning
SupportedSource for Fine-tuning (opens in a new tab)

Professional Voice Cloning beta is a managed voice-specific fine-tuning workflow with training and plan requirements, not downloadable base weights.

Knowledge cutoff
Not collected
Parameters
Not collected
Architecture
Not collected
Languages
View all 470 entries
  • Arabic (ar; default ar-SA) · Tier 1
  • Chinese (zh; default zh-CN) · Tier 1
  • Dutch (nl; default nl-NL) · Tier 1
  • English (en; default en-US) · Tier 1
  • French (fr; default fr-FR) · Tier 1
  • German (de; default de-DE) · Tier 1
  • Hebrew (he; default he-IL) · Tier 1
  • Hindi (hi; default hi-IN) · Tier 1
  • Italian (it; default it-IT) · Tier 1
  • Japanese (ja; default ja-JP) · Tier 1
  • Korean (ko; default ko-KR) · Tier 1
  • Polish (pl; default pl-PL) · Tier 1
  • Portuguese (pt; default pt-BR) · Tier 1
  • Russian (ru; default ru-RU) · Tier 1
  • Spanish (es; default es-ES) · Tier 1
  • Afrikaans (af; default af-ZA) · Tier 2
  • Albanian (sq; default sq-AL) · Tier 2
  • Amharic (am; default am-ET) · Tier 2
  • Armenian (hy; default hy-AM) · Tier 2
  • Assamese (as; default as-IN) · Tier 2
  • Azerbaijani (az; default az-AZ) · Tier 2
  • Basque (eu; default eu-ES) · Tier 2
  • Belarusian (be; default be-BY) · Tier 2
  • Bengali (bn; default bn-IN) · Tier 2
  • Bulgarian (bg; default bg-BG) · Tier 2
  • Burmese (my; default my-MM) · Tier 2
  • Cantonese (yue; default yue-HK) · Tier 2
  • Catalan (ca) · Tier 2
  • Cebuano (ceb; default ceb-PH) · Tier 2
  • Croatian (hr; default hr-HR) · Tier 2
  • Czech (cs; default cs-CZ) · Tier 2
  • Danish (da; default da-DK) · Tier 2
  • Eastern Yiddish (ydd) · Tier 2
  • Egyptian Arabic (arz) · Tier 2
  • Estonian (et; default et-EE) · Tier 2
  • Filipino (fil; default fil-PH) · Tier 2
  • Finnish (fi) · Tier 2
  • Galician (gl; default gl-ES) · Tier 2
  • Garhwali (gbm) · Tier 2
  • Georgian (ka; default ka-GE) · Tier 2
  • Greek (el; default el-GR) · Tier 2
  • Gujarati (gu; default gu-IN) · Tier 2
  • Gulf Arabic (afb) · Tier 2
  • Haitian Creole (ht; default ht-HT) · Tier 2
  • Hijazi Arabic (acw) · Tier 2
  • Hungarian (hu; default hu-HU) · Tier 2
  • Icelandic (is; default is-IS) · Tier 2
  • Indonesian (id; default id-ID) · Tier 2
  • Javanese (jv; default jv-ID) · Tier 2
  • Kannada (kn; default kn-IN) · Tier 2
  • Kazakh (kk; default kk-KZ) · Tier 2
  • Konkani (kok; default kok-IN) · Tier 2
  • Lao (lo; default lo-LA) · Tier 2
  • Latvian (lv; default lv-LV) · Tier 2
  • Libyan Arabic (ayl) · Tier 2
  • Lithuanian (lt; default lt-LT) · Tier 2
  • Luxembourgish (lb; default lb-LU) · Tier 2
  • Macedonian (mk; default mk-MK) · Tier 2
  • Maithili (mai; default mai-IN) · Tier 2
  • Malagasy (mg; default mg-MG) · Tier 2
  • Malay (ms; default ms-MY) · Tier 2
  • Malayalam (ml; default ml-IN) · Tier 2
  • Marathi (mr; default mr-IN) · Tier 2
  • Mongolian (mn; default mn-MN) · Tier 2
  • Najdi Arabic (ars) · Tier 2
  • Nepali (ne; default ne-NP) · Tier 2
  • Northern Uzbek (uzn) · Tier 2
  • Norwegian Bokmål (nb; default nb-NO) · Tier 2
  • Norwegian Nynorsk (nn; default nn-NO) · Tier 2
  • Odia (or; default or-IN) · Tier 2
  • Omani Arabic (acx) · Tier 2
  • Pashto (ps; default ps-AF) · Tier 2
  • Persian (fa; default fa-IR) · Tier 2
  • Piedmontese (pms) · Tier 2
  • Punjabi (pa; default pa-IN) · Tier 2
  • Romanian (ro; default ro-RO) · Tier 2
  • Serbian (sr; default sr-RS) · Tier 2
  • Sindhi (sd) · Tier 2
  • Sinhala (si) · Tier 2
  • Slovak (sk; default sk-SK) · Tier 2
  • Slovenian (sl; default sl-SI) · Tier 2
  • Swahili (sw; default sw-KE) · Tier 2
  • Swedish (sv; default sv-SE) · Tier 2
  • Tamil (ta; default ta-IN) · Tier 2
  • Telugu (te; default te-IN) · Tier 2
  • Thai (th; default th-TH) · Tier 2
  • Tunisian Arabic (aeb) · Tier 2
  • Turkish (tr; default tr-TR) · Tier 2
  • Ukrainian (uk; default uk-UA) · Tier 2
  • Urdu (ur; default ur-PK) · Tier 2
  • Uzbek (uz; default uz-UZ) · Tier 2
  • Vietnamese (vi; default vi-VN) · Tier 2
  • Võro (vro) · Tier 2
  • Welsh (cy) · Tier 2
  • Abadi (kbt) · Tier 3
  • Abron (abr) · Tier 3
  • Abua (abn) · Tier 3
  • Afade (aal) · Tier 3
  • Agwagwune (yay) · Tier 3
  • Akebu (keu) · Tier 3
  • Alago (ala) · Tier 3
  • Algerian Arabic (arq) · Tier 3
  • Algerian Saharan Arabic (aao) · Tier 3
  • Ambonese Malay (abs) · Tier 3
  • Anaang (anw) · Tier 3
  • Angika (anp) · Tier 3
  • Antankarana Malagasy (xmv) · Tier 3
  • Arbereshe Albanian (aae) · Tier 3
  • Ashe (ahs) · Tier 3
  • Askopan (eiv) · Tier 3
  • Asturian (ast) · Tier 3
  • Avaric (av) · Tier 3
  • Awak (awo) · Tier 3
  • Bacama (bcy) · Tier 3
  • Bade (bde) · Tier 3
  • Bagirmi Fulfulde (fui) · Tier 3
  • Bago-Kusuntu (bqg) · Tier 3
  • Baharna Arabic (abv) · Tier 3
  • Balanta-Ganja (bjt) · Tier 3
  • Bangwinji (bsj) · Tier 3
  • Banjar (bjn) · Tier 3
  • Bara Malagasy (bhr) · Tier 3
  • Barok (bjk) · Tier 3
  • Basa (bzw) · Tier 3
  • Bashkir (ba) · Tier 3
  • Batak Mandailing (btm) · Tier 3
  • Bavarian (bar) · Tier 3
  • Bayot (bda) · Tier 3
  • Betawi (bew) · Tier 3
  • Bhili (bhb) · Tier 3
  • Bhojpuri (bho) · Tier 3
  • Bilur (bxf) · Tier 3
  • Bima (bhp) · Tier 3
  • Bodo (brx; default brx-IN) · Tier 3
  • Boghom (bux) · Tier 3
  • Bokyi (bky) · Tier 3
  • Bomu (bmq) · Tier 3
  • Bondei (bou) · Tier 3
  • Borgu Fulfulde (fue) · Tier 3
  • Bosnian (bs) · Tier 3
  • Brahui (brh) · Tier 3
  • Braj (bra) · Tier 3
  • Buduma (bdm) · Tier 3
  • Buginese (bug) · Tier 3
  • Bukharic (bhh) · Tier 3
  • Bundeli (bns) · Tier 3
  • Bura-Pabir (bwr) · Tier 3
  • Burak (bys) · Tier 3
  • Cacaloxtepec Mixtec (miu) · Tier 3
  • Cakfem-Mushere (cky) · Tier 3
  • Campidanese Sardinian (sro) · Tier 3
  • Cen (cen) · Tier 3
  • Central Nahuatl (nhn) · Tier 3
  • Central Pame (pbs) · Tier 3
  • Central Pashto (pst) · Tier 3
  • Central-Eastern Niger Fulfulde (fuq) · Tier 3
  • Chadian Arabic (shu) · Tier 3
  • Chhattisgarhi (hne; default hne-IN) · Tier 3
  • Chichicapan Zapotec (zpv) · Tier 3
  • Chiga (cgg) · Tier 3
  • Chimalapa Zoque (zoh) · Tier 3
  • Chimborazo Highland Quichua (qug) · Tier 3
  • Chitwania Tharu (the) · Tier 3
  • Chuvash (cv) · Tier 3
  • Cibak (ckl) · Tier 3
  • Coastal Konjo (kjc) · Tier 3
  • Cornish (kw) · Tier 3
  • Cross River Mbembe (mfn) · Tier 3
  • Cuyamecalco Mixtec (xtu) · Tier 3
  • Dadiya (dbd) · Tier 3
  • Dazaga (dzg) · Tier 3
  • Deccan (dcc) · Tier 3
  • Degema (deg) · Tier 3
  • Dera (kna) · Tier 3
  • Dghwede (dgh) · Tier 3
  • Dhofari Arabic (adf) · Tier 3
  • Dijim-Bwilim (cfa) · Tier 3
  • Dogri (doi; default doi-IN) · Tier 3
  • Dotyali (dty) · Tier 3
  • Duya (ldb) · Tier 3
  • Eastern Bolivian Guarani (gui) · Tier 3
  • Eastern Egyptian Bedawi Arabic (avl) · Tier 3
  • Eastern Krahn (kqo) · Tier 3
  • Eastern Mari (mhr) · Tier 3
  • Eggon (ego) · Tier 3
  • Ejagham (etu) · Tier 3
  • Eleme (elm) · Tier 3
  • Eloyi (afo) · Tier 3
  • Embu (ebu) · Tier 3
  • Esan (ish) · Tier 3
  • Esperanto (eo) · Tier 3
  • Extremaduran (ext) · Tier 3
  • Fanti (fat) · Tier 3
  • Farefare (gur) · Tier 3
  • Filomena Mata-Coahuitlan Totonac (tlp) · Tier 3
  • Fipa (fip) · Tier 3
  • Gambian Wolof (wof) · Tier 3
  • Gbagyi (gbr) · Tier 3
  • Gbari (gby) · Tier 3
  • Geser-Gorom (ges) · Tier 3
  • Gheg Albanian (aln) · Tier 3
  • Glavda (glw) · Tier 3
  • Goan Konkani (gom) · Tier 3
  • Goemai (ank) · Tier 3
  • Gola (gol) · Tier 3
  • Guduf-Gava (gdf) · Tier 3
  • Guerrero Amuzgo (amu) · Tier 3
  • Gusii (guz) · Tier 3
  • Gusilay (gsl) · Tier 3
  • Gweno (gwe) · Tier 3
  • Gyaazi (gyz) · Tier 3
  • Güilá Zapotec (ztu) · Tier 3
  • Hadothi (hoj) · Tier 3
  • Hahon (hah) · Tier 3
  • Hako (hao) · Tier 3
  • Halia (hla) · Tier 3
  • Hawaiian (haw) · Tier 3
  • Herero (her) · Tier 3
  • Highland Konjo (kjk) · Tier 3
  • Huaxcaleca Nahuatl (nhq) · Tier 3
  • Huba (hbb) · Tier 3
  • Huitepec Mixtec (mxs) · Tier 3
  • Hula (hul) · Tier 3
  • Hunjara-Kaina Ke (hkk) · Tier 3
  • Hwana (hwo) · Tier 3
  • Idakho-Isukha-Tiriki (ida) · Tier 3
  • Ido (io) · Tier 3
  • Idoma (idu) · Tier 3
  • Igo (ahl) · Tier 3
  • Ikposo (kpo) · Tier 3
  • Ikwere (ikw) · Tier 3
  • Ilocano (ilo) · Tier 3
  • Interlingua (ia) · Tier 3
  • Interlingue (ie) · Tier 3
  • Irish (ga) · Tier 3
  • Isekiri (its) · Tier 3
  • Isoko (iso) · Tier 3
  • Ito (itw) · Tier 3
  • Itza (itz) · Tier 3
  • Ixtayutla Mixtec (vmj) · Tier 3
  • Izon (ijc) · Tier 3
  • Jambi Malay (jax) · Tier 3
  • Jaunsari (jns) · Tier 3
  • Jiba (juo) · Tier 3
  • Jju (kaj) · Tier 3
  • Judeo-Moroccan Arabic (aju) · Tier 3
  • Juxtlahuaca Mixtec (vmc) · Tier 3
  • Kabras (lkb) · Tier 3
  • Kachi Koli (gjk) · Tier 3
  • Kairak (ckr) · Tier 3
  • Kalabari (ijn) · Tier 3
  • Kamo (kcq) · Tier 3
  • Kanauji (bjj) · Tier 3
  • Kanembu (kbl) · Tier 3
  • Karekare (kai) · Tier 3
  • Kashmiri (ks; default ks-IN) · Tier 3
  • Kathoriya Tharu (tkt) · Tier 3
  • Keiyo (eyo) · Tier 3
  • Khana (ogo) · Tier 3
  • Khmer (km) · Tier 3
  • Kinga (zga) · Tier 3
  • Kinnauri (kfk) · Tier 3
  • Kirya-Konzel (fkk) · Tier 3
  • Kochila Tharu (thq) · Tier 3
  • Kohumono (bcs) · Tier 3
  • Kok Borok (trp) · Tier 3
  • Kol (kol) · Tier 3
  • Koma (kmy) · Tier 3
  • Konkani (individual language) (knn) · Tier 3
  • Konzo (koo) · Tier 3
  • Korwa (kfp) · Tier 3
  • Kota (kfe) · Tier 3
  • Kuanua (ksd) · Tier 3
  • Kuanyama (kua) · Tier 3
  • Kui (uki) · Tier 3
  • Kulung (bbu) · Tier 3
  • Kuot (kto) · Tier 3
  • Kurdish (ku) · Tier 3
  • Kushi (kuh) · Tier 3
  • Kwambi (kwm) · Tier 3
  • Kyrgyz (ky) · Tier 3
  • Lala-Roba (lla) · Tier 3
  • Lamang (hia) · Tier 3
  • Langi (lag) · Tier 3
  • Larike-Wakasihu (alo) · Tier 3
  • Latin (la; default la-VA) · Tier 3
  • Lezghian (lez) · Tier 3
  • Liana-Seti (ste) · Tier 3
  • Liberia Kpelle (xpe) · Tier 3
  • Liberian English (lir) · Tier 3
  • Ligurian (lij) · Tier 3
  • Lijili (mgi) · Tier 3
  • Logooli (rag) · Tier 3
  • Logudorese Sardinian (src) · Tier 3
  • Lojban (jbo) · Tier 3
  • Loloda (loa) · Tier 3
  • Longuda (lnu) · Tier 3
  • Low German (nds) · Tier 3
  • Loxicha Zapotec (ztp) · Tier 3
  • Lushai (lus) · Tier 3
  • Maasina Fulfulde (ffm) · Tier 3
  • Maba (mde) · Tier 3
  • Mafa (maf) · Tier 3
  • Mali (gcc) · Tier 3
  • Malinaltepec Me'phaa (tcf) · Tier 3
  • Maltese (mt) · Tier 3
  • Mandara (tbf) · Tier 3
  • Mandjak (mfv) · Tier 3
  • Manggarai (mqy) · Tier 3
  • Manipuri (mni) · Tier 3
  • Mansoanka (msw) · Tier 3
  • Marghi Central (mrt) · Tier 3
  • Marghi South (mfm) · Tier 3
  • Maria (mrr) · Tier 3
  • Masikoro Malagasy (msh) · Tier 3
  • Mazaltepec Zapotec (zpy) · Tier 3
  • Mazatlan Mazatec (vmz) · Tier 3
  • Mazatlan Mixe (mzl) · Tier 3
  • Mbe (mfo) · Tier 3
  • Mekeo (mek) · Tier 3
  • Meru (mer) · Tier 3
  • Mesopotamian Arabic (acm) · Tier 3
  • Mewari (mtr) · Tier 3
  • Mingrelian (xmf) · Tier 3
  • Mirandese (mwl) · Tier 3
  • Mitlatongo Mixtec (vmm) · Tier 3
  • Miya (mkf) · Tier 3
  • Mom Jango (ver) · Tier 3
  • Moroccan Arabic (ary) · Tier 3
  • Motu (meu) · Tier 3
  • Musi (mui) · Tier 3
  • Naba (mne) · Tier 3
  • Nalik (nal) · Tier 3
  • Ndonga (ndo) · Tier 3
  • Neapolitan (nap) · Tier 3
  • Ngamo (nbh) · Tier 3
  • Ngas (anc) · Tier 3
  • Ngizim (ngi) · Tier 3
  • Nigerian Fulfulde (fuv) · Tier 3
  • Nimadi (noe) · Tier 3
  • Nobiin (fia) · Tier 3
  • North Levantine Arabic (apc) · Tier 3
  • North Mesopotamian Arabic (ayp) · Tier 3
  • North Moluccan Malay (max) · Tier 3
  • Northern Betsimisaraka Malagasy (bmm) · Tier 3
  • Northern Hindko (hno) · Tier 3
  • Northern Pame (pmq) · Tier 3
  • Northern Pashto (pbu) · Tier 3
  • Norwegian (no) · Tier 3
  • Notsi (ncf) · Tier 3
  • Nyankpa (yes) · Tier 3
  • Nzanyi (nja) · Tier 3
  • Occitan (oc) · Tier 3
  • Od (odk) · Tier 3
  • Odual (odu) · Tier 3
  • Omie (aom) · Tier 3
  • Orma (orc) · Tier 3
  • Pahari-Potwari (phr) · Tier 3
  • Papuan Malay (pmy) · Tier 3
  • Pero (pip) · Tier 3
  • Petats (pex) · Tier 3
  • Piya-Kwonci (piy) · Tier 3
  • Plateau Malagasy (plt) · Tier 3
  • Pokoot (pko) · Tier 3
  • Poqomam (poc) · Tier 3
  • Pulaar (fuc) · Tier 3
  • Pular (fuf) · Tier 3
  • Qaqet (byx) · Tier 3
  • Quiotepec Chinantec (chq) · Tier 3
  • Rana Tharu (thr) · Tier 3
  • Rapoisi (kyx) · Tier 3
  • Ratahan (rth) · Tier 3
  • Rayon Zoque (zor) · Tier 3
  • Rombo (rof) · Tier 3
  • Rotokas (roo) · Tier 3
  • Sacapulteco (quv) · Tier 3
  • Saidi Arabic (aec) · Tier 3
  • Sakalava Malagasy (skg) · Tier 3
  • Sakha (sah) · Tier 3
  • Saleman (sau) · Tier 3
  • Samba Daka (ccg) · Tier 3
  • Samba Leko (ndi) · Tier 3
  • San Felipe Otlaltepec Popoloca (pow) · Tier 3
  • San Francisco Del Mar Huave (hue) · Tier 3
  • San Juan Atzingo Popoloca (poe) · Tier 3
  • San Martin Itunyoso Triqui (trq) · Tier 3
  • San Miguel El Grande Mixtec (mig) · Tier 3
  • Sanskrit (sa; default sa-IN) · Tier 3
  • Santa Catarina Albarradas Zapotec (ztn) · Tier 3
  • Santali (sat) · Tier 3
  • Saposa (sps) · Tier 3
  • Saya (say) · Tier 3
  • Siar-Lak (sjr) · Tier 3
  • Sibe (nco) · Tier 3
  • Sicilian (scn) · Tier 3
  • Sikkimese (sip) · Tier 3
  • Sinaugoro (snc) · Tier 3
  • Sinicahua Mixtec (xti) · Tier 3
  • Sipacapense (qum) · Tier 3
  • Siwai (siw) · Tier 3
  • Solos (sol) · Tier 3
  • Soninke (snk) · Tier 3
  • Southeastern Nochixtlan Mixtec (mxy) · Tier 3
  • Southern Betsimisaraka Malagasy (bzc) · Tier 3
  • Southern Pashto (pbt) · Tier 3
  • Soyaltepec Mazatec (vmp) · Tier 3
  • Sudanese Arabic (apd) · Tier 3
  • Sulka (sua) · Tier 3
  • Sundanese (su) · Tier 3
  • Tae (rob) · Tier 3
  • Tahaggart Tamahaq (thv) · Tier 3
  • Tajik (tg) · Tier 3
  • Tandroy-Mahafaly Malagasy (tdx) · Tier 3
  • Tangale (tan) · Tier 3
  • Tanosy Malagasy (txy) · Tier 3
  • Tarok (yer) · Tier 3
  • Tatar (tt) · Tier 3
  • Tedaga (tuq) · Tier 3
  • Teop (tio) · Tier 3
  • Tepinapa Chinantec (cte) · Tier 3
  • Tera (ttr) · Tier 3
  • Terei (buo) · Tier 3
  • Termanu (twu) · Tier 3
  • Tesaka Malagasy (tkg) · Tier 3
  • Tetelcingo Nahuatl (nhg) · Tier 3
  • Tibetan (bo) · Tier 3
  • Tidaa Mixtec (mtx) · Tier 3
  • Tidore (tvo) · Tier 3
  • Tigak (tgc) · Tier 3
  • Tilquiapan Zapotec (zts) · Tier 3
  • Tinputz (tpz) · Tier 3
  • Tlacoapa Me'phaa (tpl) · Tier 3
  • Tlacoatzintepec Chinantec (ctl) · Tier 3
  • Tomoip (tqp) · Tier 3
  • Tondano (tdn) · Tier 3
  • Tonsea (txs) · Tier 3
  • Tooro (ttj) · Tier 3
  • Torau (ttu) · Tier 3
  • Tsimihety Malagasy (xmw) · Tier 3
  • Tsotso (lto) · Tier 3
  • Tugen (tuy) · Tier 3
  • Tula (tul) · Tier 3
  • Tulu (tcy) · Tier 3
  • Tungag (lcm) · Tier 3
  • Turkana (tuv) · Tier 3
  • Tututepec Mixtec (mtu) · Tier 3
  • Ubaghara (byc) · Tier 3
  • Vai (vai) · Tier 3
  • Volapük (vo) · Tier 3
  • Waci Gbe (wci) · Tier 3
  • Wadiyara Koli (kxp) · Tier 3
  • Waja (wja) · Tier 3
  • Wanga (lwg) · Tier 3
  • Wapan (juk) · Tier 3
  • Waray (war) · Tier 3
  • Warji (wji) · Tier 3
  • Wemale (weo) · Tier 3
  • Western Frisian (fy) · Tier 3
  • Western Juxtlahuaca Mixtec (jmx) · Tier 3
  • Western Maninkakan (mlq) · Tier 3
  • Western Niger Fulfulde (fuh) · Tier 3
  • Western Panjabi (pnb) · Tier 3
  • Wu Chinese (wuu) · Tier 3
  • Xanaguia Zapotec (ztg) · Tier 3
  • Yace (ekr) · Tier 3
  • Yalahatan (jal) · Tier 3
  • Yekhee (ets) · Tier 3
  • Yiddish (yi) · Tier 3
  • Yutanduchi Mixtec (mab) · Tier 3
  • Zarma (dje) · Tier 3
Source for Languages (opens in a new tab)

470 language entries across 623 accepted language/locale codes. Tier 1: 15 extensively evaluated languages. Tier 2: 79 supported with more variable quality. Tier 3: 376 unevaluated, best-effort languages without text normalization. Accepted codes do not guarantee equal quality.

Context caching
Not collected
Language pack selectors
623 accepted BCP-47 language/locale codes: 241 in Tiers 1–2 and 382 in Tier 3Source for Language pack selectors (opens in a new tab)

This count includes regional codes. It is not 623 distinct languages.

Audio controls
Natural-language steering; STABLE/BALANCED/CREATIVE deliveryMode; persistent tags and [reset]; non-verbal cuesSource for Audio controls (opens in a new tab)
Speech timestamps and alignment
Word or character timestamps, with phonetic details and visemes; availability spans the supported language inventorySource for Speech timestamps and alignment (opens in a new tab)
Published price
On-Demand $25; Creator $20; Builder $17.50; Developer $15; Growth $12.50 per 1M charactersSource for Published price (opens in a new tab)

Paid plan fees provide credits shared across products. Batch pricing applies only to TTS-2.

Maximum prompt characters
Unary 2,000 UTF-16 code units; HTTP stream 4,000; WebSocket 2,000 per sendText messageSource for Maximum prompt characters (opens in a new tab)

Endpoint-specific limits; longer async jobs are available only on TTS-2. OpenAI-compatible input is documented separately as up to 4,000 characters.

Output formats
MP3, PCM, WAV, LINEAR16, OGG_OPUS, FLAC, ALAW, MULAWSource for Output formats (opens in a new tab)

Encoding support and sample rate vary by transport; OpenAI-compatible synthesis supports only its documented five formats.

Audio sample rates
Requested output 8,000–48,000 Hz; default 48,000 Hz with codec-specific restrictionsSource for Audio sample rates (opens in a new tab)

Resampling support is not a native generation-rate claim.

Voice cloning
Instant clones, plus Professional Voice Cloning beta: at least ten minutes combined, up to 50 samples / 1 GB, at most ten files per uploadSource for Voice cloning (opens in a new tab)

English fully supported; other professional-clone languages experimental. Pricing and PVC slot-limit pages disagree about low-tier access, so confirm entitlement.

Supplied context limit
Up to 2,000 characters of earlier synthesis text; not billedSource for Supplied context limit (opens in a new tab)

synthesisContext supplies prior request text. It is not a model token window or a prompt-cache guarantee.

Batch limits
1–10,000 items, 100,000 characters per item, 16 MiB total; On-Demand capped at 10,000 characters across a jobSource for Batch limits (opens in a new tab)

Queued-character budget and concurrent job limits also apply. A 24-hour delivery target is not a guaranteed SLA.

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

API model ID
inworld-tts-2
Access
Native synthesis API; account plan and concurrency limits apply.
Regions
General API region not pinned by these contracts. EU and India residency are enterprise offerings, not assumed for every request.
API endpoint URL
https://api.inworld.ai/tts/v1/voiceSource for API endpoint URL (opens in a new tab)
Maximum prompt characters
2,000 UTF-16 code unitsSource for Maximum prompt characters (opens in a new tab)
Request mode
Single JSON object with Base64 audioSource for Request mode (opens in a new tab)
Request quotas
TTS generation concurrency by plan: 5 / 10 / 50 / 150 / 500. WebSocket connections: 50 / 100 / 500 / 1,500 / 5,000; enterprise customSource for Request quotas (opens in a new tab)

Account-level limits are shared across keys. Active generations are distinct from idle WebSocket connections.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech synthesisSpeech synthesis · On-Demand1$25.001M characters
Speech synthesisSpeech synthesis · Creator2$20.001M characters
SubscriptionPlan fee · Creator3$25.00month
Speech synthesisSpeech synthesis · Builder4$17.501M characters
SubscriptionPlan fee · Builder5$100.00month
Speech synthesisSpeech synthesis · Developer6$15.001M characters
SubscriptionPlan fee · Developer7$300.00month
Speech synthesisSpeech synthesis · Growth8$12.501M characters
SubscriptionPlan fee · Growth9$1,500.00month

Rate conditions

  1. On-Demand plan: pay as you go after included trial credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. No batch discount applied. TTS native usage counts UTF-16 code units; these are not LLM tokens. Taxes, custom enterprise terms and optional add-ons are separate.
  2. Creator plan costs $25/month and includes $25 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. No batch discount applied. TTS native usage counts UTF-16 code units; these are not LLM tokens. Taxes, custom enterprise terms and optional add-ons are separate.
  3. Monthly subscription includes $25 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
  4. Builder plan costs $100/month and includes $100 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. No batch discount applied. TTS native usage counts UTF-16 code units; these are not LLM tokens. Taxes, custom enterprise terms and optional add-ons are separate.
  5. Monthly subscription includes $100 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
  6. Developer plan costs $300/month and includes $300 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. No batch discount applied. TTS native usage counts UTF-16 code units; these are not LLM tokens. Taxes, custom enterprise terms and optional add-ons are separate.
  7. Monthly subscription includes $300 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
  8. Growth plan costs $1500/month and includes $1500 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. No batch discount applied. TTS native usage counts UTF-16 code units; these are not LLM tokens. Taxes, custom enterprise terms and optional add-ons are separate.
  9. Monthly subscription includes $1500 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
Pricing source (opens in a new tab)

Data & enterprise terms

Inworld terms exclude nonpublic inputs/outputs from general model training, with feedback and trust/safety exceptions. ZDR is configurable and has product-specific exceptions; it is not a universal default. Pricing lists a Growth add-on, while the ZDR guide limits self-serve controls to Enterprise/Enterprise Trial. Confirm the actual workspace setting and contract. Clone samples and voice-design creation inputs are retained.

Read the service policy (opens in a new tab)
API model ID
inworld-tts-2
Access
Native synthesis API; account plan and concurrency limits apply.
Regions
General API region not pinned by these contracts. EU and India residency are enterprise offerings, not assumed for every request.
API endpoint URL
https://api.inworld.ai/tts/v1/voice:streamSource for API endpoint URL (opens in a new tab)
Maximum prompt characters
4,000 UTF-16 code unitsSource for Maximum prompt characters (opens in a new tab)
Request mode
Streaming JSON results with Base64 audio chunksSource for Request mode (opens in a new tab)
Request quotas
TTS generation concurrency by plan: 5 / 10 / 50 / 150 / 500. WebSocket connections: 50 / 100 / 500 / 1,500 / 5,000; enterprise customSource for Request quotas (opens in a new tab)

Account-level limits are shared across keys. Active generations are distinct from idle WebSocket connections.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech synthesisSpeech synthesis · On-Demand1$25.001M characters
Speech synthesisSpeech synthesis · Creator2$20.001M characters
SubscriptionPlan fee · Creator3$25.00month
Speech synthesisSpeech synthesis · Builder4$17.501M characters
SubscriptionPlan fee · Builder5$100.00month
Speech synthesisSpeech synthesis · Developer6$15.001M characters
SubscriptionPlan fee · Developer7$300.00month
Speech synthesisSpeech synthesis · Growth8$12.501M characters
SubscriptionPlan fee · Growth9$1,500.00month

Rate conditions

  1. On-Demand plan: pay as you go after included trial credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. No batch discount applied. TTS native usage counts UTF-16 code units; these are not LLM tokens. Taxes, custom enterprise terms and optional add-ons are separate.
  2. Creator plan costs $25/month and includes $25 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. No batch discount applied. TTS native usage counts UTF-16 code units; these are not LLM tokens. Taxes, custom enterprise terms and optional add-ons are separate.
  3. Monthly subscription includes $25 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
  4. Builder plan costs $100/month and includes $100 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. No batch discount applied. TTS native usage counts UTF-16 code units; these are not LLM tokens. Taxes, custom enterprise terms and optional add-ons are separate.
  5. Monthly subscription includes $100 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
  6. Developer plan costs $300/month and includes $300 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. No batch discount applied. TTS native usage counts UTF-16 code units; these are not LLM tokens. Taxes, custom enterprise terms and optional add-ons are separate.
  7. Monthly subscription includes $300 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
  8. Growth plan costs $1500/month and includes $1500 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. No batch discount applied. TTS native usage counts UTF-16 code units; these are not LLM tokens. Taxes, custom enterprise terms and optional add-ons are separate.
  9. Monthly subscription includes $1500 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
Pricing source (opens in a new tab)

Data & enterprise terms

Inworld terms exclude nonpublic inputs/outputs from general model training, with feedback and trust/safety exceptions. ZDR is configurable and has product-specific exceptions; it is not a universal default. Pricing lists a Growth add-on, while the ZDR guide limits self-serve controls to Enterprise/Enterprise Trial. Confirm the actual workspace setting and contract. Clone samples and voice-design creation inputs are retained.

Read the service policy (opens in a new tab)
API model ID
inworld-tts-2
Access
Native synthesis API; account plan and concurrency limits apply.
Regions
General API region not pinned by these contracts. EU and India residency are enterprise offerings, not assumed for every request.
API endpoint URL
wss://api.inworld.ai/tts/v1/voice:streamBidirectionalSource for API endpoint URL (opens in a new tab)
Maximum prompt characters
2,000 UTF-16 code units per sendText messageSource for Maximum prompt characters (opens in a new tab)
Request mode
Bidirectional text/audio contexts; explicit flush and close; SENTENCE_BOUNDARY automatic segmentation is PreviewSource for Request mode (opens in a new tab)
Request quotas
TTS generation concurrency by plan: 5 / 10 / 50 / 150 / 500. WebSocket connections: 50 / 100 / 500 / 1,500 / 5,000; enterprise customSource for Request quotas (opens in a new tab)

Account-level limits are shared across keys. Active generations are distinct from idle WebSocket connections.

Session duration
Session closes after ten minutes of inactivity across contextsSource for Session duration (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech synthesisSpeech synthesis · On-Demand1$25.001M characters
Speech synthesisSpeech synthesis · Creator2$20.001M characters
SubscriptionPlan fee · Creator3$25.00month
Speech synthesisSpeech synthesis · Builder4$17.501M characters
SubscriptionPlan fee · Builder5$100.00month
Speech synthesisSpeech synthesis · Developer6$15.001M characters
SubscriptionPlan fee · Developer7$300.00month
Speech synthesisSpeech synthesis · Growth8$12.501M characters
SubscriptionPlan fee · Growth9$1,500.00month

Rate conditions

  1. On-Demand plan: pay as you go after included trial credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. No batch discount applied. TTS native usage counts UTF-16 code units; these are not LLM tokens. Taxes, custom enterprise terms and optional add-ons are separate.
  2. Creator plan costs $25/month and includes $25 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. No batch discount applied. TTS native usage counts UTF-16 code units; these are not LLM tokens. Taxes, custom enterprise terms and optional add-ons are separate.
  3. Monthly subscription includes $25 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
  4. Builder plan costs $100/month and includes $100 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. No batch discount applied. TTS native usage counts UTF-16 code units; these are not LLM tokens. Taxes, custom enterprise terms and optional add-ons are separate.
  5. Monthly subscription includes $100 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
  6. Developer plan costs $300/month and includes $300 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. No batch discount applied. TTS native usage counts UTF-16 code units; these are not LLM tokens. Taxes, custom enterprise terms and optional add-ons are separate.
  7. Monthly subscription includes $300 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
  8. Growth plan costs $1500/month and includes $1500 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. No batch discount applied. TTS native usage counts UTF-16 code units; these are not LLM tokens. Taxes, custom enterprise terms and optional add-ons are separate.
  9. Monthly subscription includes $1500 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
Pricing source (opens in a new tab)

Data & enterprise terms

Inworld terms exclude nonpublic inputs/outputs from general model training, with feedback and trust/safety exceptions. ZDR is configurable and has product-specific exceptions; it is not a universal default. Pricing lists a Growth add-on, while the ZDR guide limits self-serve controls to Enterprise/Enterprise Trial. Confirm the actual workspace setting and contract. Clone samples and voice-design creation inputs are retained.

Read the service policy (opens in a new tab)
API model ID
inworld-tts-2
Access
Native synthesis API; account plan and concurrency limits apply.
Regions
General API region not pinned by these contracts. EU and India residency are enterprise offerings, not assumed for every request.
API endpoint URL
https://api.inworld.ai/v1/audio/speechSource for API endpoint URL (opens in a new tab)
Maximum prompt characters
4,000 charactersSource for Maximum prompt characters (opens in a new tab)
Request mode
Raw audio bytes or Server-Sent EventsSource for Request mode (opens in a new tab)
Request quotas
TTS generation concurrency by plan: 5 / 10 / 50 / 150 / 500. WebSocket connections: 50 / 100 / 500 / 1,500 / 5,000; enterprise customSource for Request quotas (opens in a new tab)

Account-level limits are shared across keys. Active generations are distinct from idle WebSocket connections.

Output formats
mp3, opus, flac, wav, pcmSource for Output formats (opens in a new tab)
Audio sample rates
MP3/Opus/FLAC/WAV: 48 kHz mono; raw PCM16: 24 kHz monoSource for Audio sample rates (opens in a new tab)
Authentication
Bearer API key; other native TTS routes use Basic credentialsSource for Authentication (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech synthesisSpeech synthesis · On-Demand1$25.001M characters
Speech synthesisSpeech synthesis · Creator2$20.001M characters
SubscriptionPlan fee · Creator3$25.00month
Speech synthesisSpeech synthesis · Builder4$17.501M characters
SubscriptionPlan fee · Builder5$100.00month
Speech synthesisSpeech synthesis · Developer6$15.001M characters
SubscriptionPlan fee · Developer7$300.00month
Speech synthesisSpeech synthesis · Growth8$12.501M characters
SubscriptionPlan fee · Growth9$1,500.00month

Rate conditions

  1. On-Demand plan: pay as you go after included trial credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. No batch discount applied. TTS native usage counts UTF-16 code units; these are not LLM tokens. Taxes, custom enterprise terms and optional add-ons are separate.
  2. Creator plan costs $25/month and includes $25 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. No batch discount applied. TTS native usage counts UTF-16 code units; these are not LLM tokens. Taxes, custom enterprise terms and optional add-ons are separate.
  3. Monthly subscription includes $25 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
  4. Builder plan costs $100/month and includes $100 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. No batch discount applied. TTS native usage counts UTF-16 code units; these are not LLM tokens. Taxes, custom enterprise terms and optional add-ons are separate.
  5. Monthly subscription includes $100 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
  6. Developer plan costs $300/month and includes $300 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. No batch discount applied. TTS native usage counts UTF-16 code units; these are not LLM tokens. Taxes, custom enterprise terms and optional add-ons are separate.
  7. Monthly subscription includes $300 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
  8. Growth plan costs $1500/month and includes $1500 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. No batch discount applied. TTS native usage counts UTF-16 code units; these are not LLM tokens. Taxes, custom enterprise terms and optional add-ons are separate.
  9. Monthly subscription includes $1500 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
Pricing source (opens in a new tab)

Data & enterprise terms

Inworld terms exclude nonpublic inputs/outputs from general model training, with feedback and trust/safety exceptions. ZDR is configurable and has product-specific exceptions; it is not a universal default. Pricing lists a Growth add-on, while the ZDR guide limits self-serve controls to Enterprise/Enterprise Trial. Confirm the actual workspace setting and contract. Clone samples and voice-design creation inputs are retained.

Read the service policy (opens in a new tab)
API model ID
inworld-tts-2
Access
Preview. TTS-2 only. Account-level job concurrency, queued text and plan size limits apply.
Regions
General API region not pinned by these contracts. EU and India residency are enterprise offerings, not assumed for every request.
API endpoint URL
https://api.inworld.ai/tts/v1/voice:synthesizeAsyncSource for API endpoint URL (opens in a new tab)
Maximum prompt characters
100,000 characters per job; On-Demand 10,000Source for Maximum prompt characters (opens in a new tab)
Batch limits
One long synthesis request per jobSource for Batch limits (opens in a new tab)
Request quotas
5 / 10 / 50 / 150 / 500 concurrent jobs by plan; batch queued-character budgets 1M / 2M / 10M / 30M / 100MSource for Request quotas (opens in a new tab)

Async and batch pools are separate. Over-limit submits are rejected, not silently queued.

Data retention
Results normally expire about seven days after completion. ZDR requires outputConfig.resultsUri to deliver to customer storage; otherwise submit is rejectedSource for Data retention (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech synthesisSpeech synthesis · On-Demand1$25.001M characters
Speech synthesisSpeech synthesis · Creator2$20.001M characters
SubscriptionPlan fee · Creator3$25.00month
Speech synthesisSpeech synthesis · Builder4$17.501M characters
SubscriptionPlan fee · Builder5$100.00month
Speech synthesisSpeech synthesis · Developer6$15.001M characters
SubscriptionPlan fee · Developer7$300.00month
Speech synthesisSpeech synthesis · Growth8$12.501M characters
SubscriptionPlan fee · Growth9$1,500.00month

Rate conditions

  1. On-Demand plan: pay as you go after included trial credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. No batch discount applied. TTS native usage counts UTF-16 code units; these are not LLM tokens. Taxes, custom enterprise terms and optional add-ons are separate.
  2. Creator plan costs $25/month and includes $25 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. No batch discount applied. TTS native usage counts UTF-16 code units; these are not LLM tokens. Taxes, custom enterprise terms and optional add-ons are separate.
  3. Monthly subscription includes $25 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
  4. Builder plan costs $100/month and includes $100 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. No batch discount applied. TTS native usage counts UTF-16 code units; these are not LLM tokens. Taxes, custom enterprise terms and optional add-ons are separate.
  5. Monthly subscription includes $100 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
  6. Developer plan costs $300/month and includes $300 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. No batch discount applied. TTS native usage counts UTF-16 code units; these are not LLM tokens. Taxes, custom enterprise terms and optional add-ons are separate.
  7. Monthly subscription includes $300 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
  8. Growth plan costs $1500/month and includes $1500 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. No batch discount applied. TTS native usage counts UTF-16 code units; these are not LLM tokens. Taxes, custom enterprise terms and optional add-ons are separate.
  9. Monthly subscription includes $1500 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
Pricing source (opens in a new tab)

Data & enterprise terms

Inworld terms exclude nonpublic inputs/outputs from general model training, with feedback and trust/safety exceptions. ZDR is configurable and has product-specific exceptions; it is not a universal default. Pricing lists a Growth add-on, while the ZDR guide limits self-serve controls to Enterprise/Enterprise Trial. Confirm the actual workspace setting and contract. Clone samples and voice-design creation inputs are retained. Async/batch artifacts are normally retained about seven days. ZDR jobs require a customer-owned pre-signed output destination.

Read the service policy (opens in a new tab)
API model ID
inworld-tts-2
Access
Preview. TTS-2 only. Account-level job concurrency, queued text and plan size limits apply.
Regions
General API region not pinned by these contracts. EU and India residency are enterprise offerings, not assumed for every request.
API endpoint URL
https://api.inworld.ai/tts/v1/voice:synthesizeBatchSource for API endpoint URL (opens in a new tab)
Maximum prompt characters
100,000 characters per item; On-Demand 10,000 across the entire jobSource for Maximum prompt characters (opens in a new tab)
Batch limits
1–10,000 items, 100,000 characters per item, 16 MiB total; On-Demand capped at 10,000 characters across a jobSource for Batch limits (opens in a new tab)

Queued-character budget and concurrent job limits also apply. A 24-hour delivery target is not a guaranteed SLA.

Request quotas
5 / 10 / 50 / 150 / 500 concurrent jobs by plan; batch queued-character budgets 1M / 2M / 10M / 30M / 100MSource for Request quotas (opens in a new tab)

Async and batch pools are separate. Over-limit submits are rejected, not silently queued.

Data retention
Results normally expire about seven days after completion. ZDR requires outputConfig.resultsUri to deliver to customer storage; otherwise submit is rejectedSource for Data retention (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech synthesisBatch speech synthesis · On-Demand1$20.001M characters
Speech synthesisBatch speech synthesis · Creator2$16.001M characters
SubscriptionPlan fee · Creator3$25.00month
Speech synthesisBatch speech synthesis · Builder4$14.001M characters
SubscriptionPlan fee · Builder5$100.00month
Speech synthesisBatch speech synthesis · Developer6$12.001M characters
SubscriptionPlan fee · Developer7$300.00month
Speech synthesisBatch speech synthesis · Growth8$10.001M characters
SubscriptionPlan fee · Growth9$1,500.00month

Rate conditions

  1. On-Demand plan: pay as you go after included trial credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. Calculated as 80% of the TTS-2 tier rate under the documented 20% batch discount. Batch turnaround is not realtime. Taxes, custom enterprise terms and optional add-ons are separate.
  2. Creator plan costs $25/month and includes $25 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. Calculated as 80% of the TTS-2 tier rate under the documented 20% batch discount. Batch turnaround is not realtime. Taxes, custom enterprise terms and optional add-ons are separate.
  3. Monthly subscription includes $25 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
  4. Builder plan costs $100/month and includes $100 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. Calculated as 80% of the TTS-2 tier rate under the documented 20% batch discount. Batch turnaround is not realtime. Taxes, custom enterprise terms and optional add-ons are separate.
  5. Monthly subscription includes $100 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
  6. Developer plan costs $300/month and includes $300 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. Calculated as 80% of the TTS-2 tier rate under the documented 20% batch discount. Batch turnaround is not realtime. Taxes, custom enterprise terms and optional add-ons are separate.
  7. Monthly subscription includes $300 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
  8. Growth plan costs $1500/month and includes $1500 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. Calculated as 80% of the TTS-2 tier rate under the documented 20% batch discount. Batch turnaround is not realtime. Taxes, custom enterprise terms and optional add-ons are separate.
  9. Monthly subscription includes $1500 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
Pricing source (opens in a new tab)Pricing source (opens in a new tab)

Data & enterprise terms

Inworld terms exclude nonpublic inputs/outputs from general model training, with feedback and trust/safety exceptions. ZDR is configurable and has product-specific exceptions; it is not a universal default. Pricing lists a Growth add-on, while the ZDR guide limits self-serve controls to Enterprise/Enterprise Trial. Confirm the actual workspace setting and contract. Clone samples and voice-design creation inputs are retained. Async/batch artifacts are normally retained about seven days. ZDR jobs require a customer-owned pre-signed output destination.

Read the service policy (opens in a new tab)
API model ID
inworld/inworld-tts-2
Access
Listed in LiveKit Inference; no separate Inworld key required. Host plan, default voice support and account limits apply.
Regions
Global. The model row does not list a dedicated EU endpoint.
Languages
View all 94 entries
  • en
  • zh
  • ja
  • ko
  • ru
  • it
  • es
  • pt
  • fr
  • de
  • pl
  • nl
  • hi
  • he
  • ar
  • af
  • sq
  • am
  • hy
  • as
  • az
  • eu
  • be
  • bn
  • bg
  • my
  • yue
  • ca
  • ceb
  • hr
  • cs
  • da
  • yih
  • arz
  • et
  • fil
  • fi
  • gl
  • gbm
  • ka
  • el
  • gu
  • afb
  • ht
  • acw
  • hu
  • is
  • id
  • jv
  • kn
  • kk
  • kok
  • lo
  • lv
  • ayl
  • lt
  • lb
  • mk
  • mai
  • mg
  • ms
  • ml
  • mr
  • mn
  • ars
  • ne
  • uzn
  • nb
  • nn
  • or
  • acx
  • ps
  • fa
  • pms
  • pa
  • ro
  • sr
  • sd
  • si
  • sk
  • sl
  • sw
  • sv
  • ta
  • te
  • th
  • aeb
  • tr
  • uk
  • ur
  • uz
  • vi
  • vro
  • cy
Source for Languages (opens in a new tab)

Host language table is retained independently of native tiers and locale aliases.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech synthesisSpeech synthesis · Build / Ship1$25.001M characters
Speech synthesisSpeech synthesis · Scale1$15.001M characters

Rate conditions

  1. Published LiveKit Inference rate; plan fees, included credits, default-voice compatibility and enterprise terms are separate.
Pricing source (opens in a new tab)

Data & enterprise terms

LiveKit documents zero retention for inference content by default, including underlying providers. Optional observability and custom-voice storage have separate handling.

Read the service policy (opens in a new tab)

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Inworld API

inworld-tts-2
Not verified

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

How it works
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

How to enable it
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Usage fields
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Billing rules
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Inworld API

inworld-tts-2
Not verified

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

How it works
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

How to enable it
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Usage fields
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Billing rules
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Inworld API

inworld-tts-2
Not verified

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

How it works
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

How to enable it
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Usage fields
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Billing rules
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Inworld API

inworld-tts-2
Not verified

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

How it works
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

How to enable it
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Usage fields
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Billing rules
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Inworld API

inworld-tts-2
Not verified

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

How it works
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

How to enable it
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Usage fields
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Billing rules
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Inworld API

inworld-tts-2
Not verified

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

How it works
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

How to enable it
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Usage fields
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Billing rules
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

LiveKit Inference

inworld/inworld-tts-2
Not verified

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

How it works
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

How to enable it
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Usage fields
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Billing rules
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Voice choices

3 voices

Choose a voice within Realtime TTS-2. These are API voice identifiers, not additional model releases. Source links document each voice.

Published voice catalog
Voice / API IDLanguage & accentDelivery
AlexAlexEnglishEnergetic and expressive mid-range male voice, with a mildly nasal quality. Public catalog example, not the full workspace voice inventory.Voice source (opens in a new tab)
AshleyAshleyEnglishA warm, natural female voice. Public catalog example, not the full workspace voice inventory.Voice source (opens in a new tab)
DennisDennisEnglishMiddle-aged man with a smooth, calm and friendly voice. Public catalog example, not the full workspace voice inventory.Voice source (opens in a new tab)

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Inworld grants limited service/model access and reserves model IP under its proprietary terms, including separately contracted customer-hosted deployment. The TTS-1 research release publishes training/modeling code, not the production TTS model weights. Current TTS/STT release identities are established in the native catalog; routed third-party models are excluded.

Classification evidence (opens in a new tab)

Lifecycle dates

Native model release5 May 2026Source (opens in a new tab)
Marketing page labels general availability31 Aug 2026Source (opens in a new tab)
Steering instructions persist until replaced/reset6 Aug 2026Source (opens in a new tab)

Sources reviewed