Voxtral 3
·
A speech model family and voice-agent SDK combining transcription, speech generation and tool calls. Separate models handle listening and speaking so teams can choose their reasoning model.
- Reviewed tasks
- Speech
- Reviewed modalities
- Text, Audio
- Deployment paths
- Hosted API, Vendor-arranged deployment
- Focus / inputs
- Speech recognition and speech generation
- Availability / restrictions
- Mistral API; private-cloud and on-premises deployment arranged with Mistral. Public weight availability is not established by this announcement.
- Licence category
- Unknown
- Licence / terms
- Provider terms; self-deployment terms require confirmation with Mistral.
Variants, limits and list prices
Values are copied from the linked first-party pages as stated, with the date each group was checked. Unknown means the pages checked do not state the value. Prices are list prices, not a quote or a ranking.
| Field | Voxtral Mini Transcribe | Voxtral Mini Transcribe Realtime | Voxtral Small Transcribe | Voxtral Mini TTS 3 |
|---|---|---|---|---|
| API identifier | voxtral-mini-transcribe-3-0 | Unknown | Unknown | Unknown |
| Released | Unknown | Unknown | Unknown | Unknown |
| Status and retirement | Public preview, dated 20 October 2026. | Unknown | Unknown | Unknown |
| Lifecycle checked | Checked | Checked | Checked | Checked |
| Context window | Context 32k | Unknown | Unknown | Unknown |
| Max input | Unknown | Unknown | Unknown | Unknown |
| Max output | Unknown | Unknown | Unknown | Unknown |
| Rate limits | Unknown | Unknown | Unknown | Unknown |
| Limit notes | Audio duration limit not stated. | Unknown | Unknown | Unknown |
| Limits checked | Checked | Checked | Checked | Checked |
| Base input price | 0.0035 USD/min (Batch transcription) | 0.008 USD/min (Realtime transcription) | 0.004 USD/min (Transcription) | 13 USD/1M chars (Speech generation) |
| Base output price | Unknown | Unknown | Unknown | Unknown |
| Cache-read price | Unknown | Unknown | Unknown | Unknown |
| Price conditions | Batch transcription: input 0.0035 USD/min. The Voxtral 3 announcement states the same rate. | Realtime transcription: input 0.008 USD/min. | Transcription: input 0.004 USD/min. | Speech generation: input 13 USD/1M chars. |
| Prices checked | Checked | Checked | Checked | Checked |
| Knowledge cutoff | Unknown | Unknown | Unknown | Unknown |
| Cutoff checked | Checked | Checked | Checked | Checked |
- Voxtral Mini Transcribe: Served through the /v1/audio/transcriptions endpoint.
Parameters and weights
Unknown: the first-party pages checked publish no parameter count or weights.