Gladia API · async
Provider source (opens in a new tab)- API model ID
solaria-1- Access
- POST https://api.gladia.io/v2/pre-recorded with audio_url, model and options; upload first or provide an external URL. Receive callback/webhook or poll results when retention settings allow.
- Regions
- EU and US regional infrastructure; verify account routing for this transport
- Audio duration limits
- Prerecorded: 135 minutes per request; Enterprise up to 4 h 15 minSource for Audio duration limits (opens in a new tab)
- Maximum audio file
- 1,000 MB per prerecorded fileSource for Maximum audio file (opens in a new tab)
- Audio channels
- 1–2 channels; channels detected from the source fileSource for Audio channels (opens in a new tab)
- Concurrent requests
- Free: 3 active jobs. Paid defaults: 25 active jobs plus up to 300 queued. Enterprise by agreement.Source for Concurrent requests (opens in a new tab)
- Billing basis
- Stereo with different content bills twice; identical-content channels bill onceSource for Billing basis (opens in a new tab)
- Languages
- Source for Languages (opens in a new tab)
View all 99 entries
- af
- am
- ar
- as
- az
- ba
- be
- bg
- bn
- bo
- br
- bs
- ca
- cs
- cy
- da
- de
- el
- en
- es
- et
- eu
- fa
- fi
- fo
- fr
- gl
- gu
- ha
- haw
- he
- hi
- hr
- ht
- hu
- hy
- id
- is
- it
- ja
- jw
- ka
- kk
- km
- kn
- ko
- la
- lb
- ln
- lo
- lt
- lv
- mg
- mi
- mk
- ml
- mn
- mr
- ms
- mt
- my
- ne
- nl
- nn
- no
- oc
- pa
- pl
- ps
- pt
- ro
- ru
- sa
- sd
- si
- sk
- sl
- sn
- so
- sq
- sr
- su
- sv
- sw
- ta
- te
- tg
- th
- tk
- tl
- tr
- tt
- uk
- ur
- uz
- vi
- yi
- yo
- zh
- Streaming
- Not supportedSource for Streaming (opens in a new tab)
- diarization
- SupportedSource for diarization (opens in a new tab)
- Translation pipeline
- Optional transcript translation; base and enhanced documented in feature guide; batch additionally appears in schemaSource for Translation pipeline (opens in a new tab)
- Entity recognition pipeline
- Optional NER, labeled Alpha in its guideSource for Entity recognition pipeline (opens in a new tab)
- Sentiment analysis pipeline
- Optional sentence-level sentiment and emotion analysis of transcript textSource for Sentiment analysis pipeline (opens in a new tab)
- Transcript redaction
- Optional PII text redaction with markers or masks and configurable entity presetsSource for Transcript redaction (opens in a new tab)
- Summarization pipeline
- Optional general, concise or bullet_points transcript summarySource for Summarization pipeline (opens in a new tab)
- Automatic chapter generation
- Not supportedSource for Automatic chapter generation (opens in a new tab)
- Included free allowance
- One-time €50 credit grant, no monthly resetSource for Included free allowance (opens in a new tab)
- Data retention
- Paid audio/transcripts: 3 weeks; free: 1 year. Enterprise ZDR requires external URL and callbacks.Source for Data retention (opens in a new tab)
Top-level model parameter; omission defaults to solaria-1.
Live has a different 3-hour session limit.
99 explicit request codes; wo is absent despite appearing in the language guide.
Asynchronous completed file result, not a live stream.
Documented for prerecorded files. Speaker-count values are hints, not enforced minimum/maximum counts. Channel splitting is a different feature.
No independent creator/checkpoint ownership established. Translation does not produce speech audio.
A preset name does not certify legal compliance or prove redaction of the source audio.
Discontinued; parameter is accepted but ignored. Custom LLM prompts are a different workflow.
Prices retain their published currencies and billing units below.
| Category | Usage | Rate | Unit |
|---|---|---|---|
| Speech recognition | Starter async transcription1 | $0.61 | audio hour |
| Speech recognition | Growth · as low as async transcription2 | $0.20 | audio hour |
Rate conditions
- Published pay-as-you-go rate through prepaid credit wallet. Same plan rates for supported Solaria models. Core audio-intelligence features are bundled; Audio-to-LLM uses external model rates plus an unspecified platform fee. Different-content stereo channels are billed as two audios; identical-content channels are billed once. Custom Enterprise bundling and prices require a quote.
- Advertised lower bound requiring upfront commitment and volume agreement; not a universal pay-as-you-go price. Same plan rates for supported Solaria models. Core audio-intelligence features are bundled; Audio-to-LLM uses external model rates plus an unspecified platform fee. Different-content stereo channels are billed as two audios; identical-content channels are billed once. Custom Enterprise bundling and prices require a quote.
Data & enterprise terms
Paid defaults: audio and transcripts 3 weeks, API metadata 1 year, logs an unspecified limited period. Free defaults retain all four data types for 1 year. Enterprise custom retention value 0 means deletion within 24 hours; separate ZDR means ephemeral processing and no later retrieval. ZDR disables file upload and polling: supply an external audio URL and receive callbacks. The compliance hub says no training without explicit agreement; a pricing blog says Starter training may be enabled by default, so confirm the applicable account agreement.
Read the service policy (opens in a new tab)