Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Soniox / Soniox TTS

TTS v1

First production Soniox speech-generation model, promoted from preview and later replaced by v2.

Speech & voice
retiredClosed weightsText-to-speech
Official documentation (opens in a new tab)Reviewed 13 Oct 2026
5 of 16 specification fields collected
Context windowNot collectedAwaiting source review
Maximum outputNot collectedAwaiting source review
Input billingNot collectedSoniox API
Output billingNot collectedNo inferred price

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
Input modalities
TextSource for Input modalities (opens in a new tab)
Output modalities
AudioSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
SupportedSource for Streaming (opens in a new tab)
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
2026-04-29Source for Release date (opens in a new tab)
Parameters
Not collected
Architecture
Not collected
Languages
View all 62 entries
  • Afrikaans (af)
  • Arabic (ar)
  • Azerbaijani (az)
  • Belarusian (be)
  • Bulgarian (bg)
  • Bengali (bn)
  • Bosnian (bs)
  • Catalan (ca)
  • Czech (cs)
  • Welsh (cy)
  • Danish (da)
  • German (de)
  • Greek (el)
  • English (en)
  • Spanish (es)
  • Estonian (et)
  • Basque (eu)
  • Persian (fa)
  • Finnish (fi)
  • French (fr)
  • Galician (gl)
  • Gujarati (gu)
  • Hebrew (he)
  • Hindi (hi)
  • Croatian (hr)
  • Hungarian (hu)
  • Indonesian (id)
  • Icelandic (is)
  • Italian (it)
  • Japanese (ja)
  • Kazakh (kk)
  • Kannada (kn)
  • Korean (ko)
  • Lithuanian (lt)
  • Latvian (lv)
  • Macedonian (mk)
  • Malayalam (ml)
  • Marathi (mr)
  • Malay (ms)
  • Dutch (nl)
  • Norwegian (no)
  • Punjabi (pa)
  • Polish (pl)
  • Portuguese (pt)
  • Romanian (ro)
  • Russian (ru)
  • Slovak (sk)
  • Slovenian (sl)
  • Albanian (sq)
  • Serbian (sr)
  • Sundanese (su)
  • Swedish (sv)
  • Swahili (sw)
  • Tamil (ta)
  • Telugu (te)
  • Thai (th)
  • Tagalog (tl)
  • Turkish (tr)
  • Ukrainian (uk)
  • Urdu (ur)
  • Vietnamese (vi)
  • Chinese (zh)
Source for Languages (opens in a new tab)

Historical v1 response example; not a live inventory or a current v2 language guarantee.

Context caching
Not collected

Access & pricing

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

Soniox API

Provider source (opens in a new tab)
API model ID
tts-rt-v1
Access
Original v1 is retired. Its ID now routes to v2; the preview ID was already an alias of v1.
Regions
Historical deployment region not established.
Equivalent API aliases
tts-rt-v1-previewSource for Equivalent API aliases (opens in a new tab)

Preview was promoted to this same production release, not counted as another checkpoint.

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

Provider states submitted content is not used to train or improve models. Real-time audio/transcript content is not retained; async files and transcripts are stored, deletable by the customer and automatically removed after 30 days. Operational usage metadata is retained. Regional residency excludes account, billing and other system data.

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.

Soniox API

tts-rt-v1
Not verified

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

How it works
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

How to enable it
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Usage fields
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Billing rules
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

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

Voice choices

28 voices

Choose a voice within TTS v1. These are API voice identifiers, not additional model releases. Source links document each voice.

Published voice catalog
Voice / API IDLanguage & accentDelivery
MayaMayaMultilingual according to v1 documentationHistorical OpenAPI voice example; female presentation.Voice source (opens in a new tab)
DanielDanielMultilingual according to v1 documentationHistorical OpenAPI voice example; male presentation.Voice source (opens in a new tab)
NoahNoahMultilingual according to v1 documentationHistorical OpenAPI voice example; male presentation.Voice source (opens in a new tab)
NinaNinaMultilingual according to v1 documentationHistorical OpenAPI voice example; female presentation.Voice source (opens in a new tab)
EmmaEmmaMultilingual according to v1 documentationHistorical OpenAPI voice example; female presentation.Voice source (opens in a new tab)
JackJackMultilingual according to v1 documentationHistorical OpenAPI voice example; male presentation.Voice source (opens in a new tab)
AdrianAdrianMultilingual according to v1 documentationHistorical OpenAPI voice example; male presentation.Voice source (opens in a new tab)
ClaireClaireMultilingual according to v1 documentationHistorical OpenAPI voice example; female presentation.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

The provider identifies its hosted models as Soniox intellectual property, grants limited service access and prohibits extraction/reverse engineering. Native release documentation and historical reports establish these model identities; no public weight license is inferred from SDK availability.

Classification evidence (opens in a new tab)

Lifecycle dates

First TTS model preview; later promoted under v1 ID23 Apr 2026Source (opens in a new tab)
Promoted to production; preview ID became an alias29 Apr 2026Source (opens in a new tab)
Original v1 retired; requests now routed to v231 Aug 2026Source (opens in a new tab)

Sources reviewed