Capabilities
Explore what Voxtral TTS 26.03 supports, then use the API section for a request tailored to this model.
Languages
Model Information
- Provider
- Mistral AI
- Product
- Text-to-Speech
- Release Date
- Mar 23, 2026
- Data Policy
- Configurable
- Region
- Global
- Input
- Text
- Output
- Audio
Playground
Try Voxtral TTS 26.03 by Mistral AI. Requests use the selected workspace’s credits and API pricing.
Providers
Compare available endpoints, pricing, and context limits for Voxtral TTS 26.03.
| Provider | Context | Output | Input Price | Output Price | Endpoint |
|---|---|---|---|---|---|
| Mistral AI | Not specified | Audio | $13.60 / 1M characters | — | mistral/voxtral-mini-tts-2603:mistral |
Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max chars | 2000 |
| Formats | mp3, opus, flac, wav |
Provider Notes
Voxtral Mini TTS 2603 requires exactly one voice source: pass a saved Mistral voice ID through the common voice field, or set provider.options.mistral.ref_audio to base64-encoded reference audio while leaving voice as auto. Mistral does not define a default voice, so voice=auto without ref_audio fails validation before dispatch.
Performance
Status
Current catalog availability. Your workspace’s access is checked separately before a request runs.
A live availability check is not available right now.
Getting Started
Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.
curl "$AUDIOLAB_API_URL/v1/audio/speech" \
-H "Authorization: Bearer $AUDIOLAB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mistral/voxtral-mini-tts-2603",
"input": "Make every word count.",
"voice": "YOUR_MISTRAL_VOICE_ID",
"response_format": "mp3"
}' --output speech.mp3Request Parameters
Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.
| Parameter | Details |
|---|---|
model | mistral/voxtral-mini-tts-2603 — Required model identifier. |
ref_audio (base64 reference audio; use instead of voice) | View Accepted Values |
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max chars | 2000 |
| Formats | mp3, opus, flac, wav |
Similar Models
Explore more text-to-speech and compare their capabilities.
| Model | Context | Input Price | Output Price |
|---|---|---|---|
| Voxtral TTS LatestMistral AI | Not specified | $13.60 / 1M characters | — |
| Sonic 3.6Cartesia | Not specified | $38.25 / 1M characters | — |
| Sonic 3.6 (2026-08-27)Cartesia | Not specified | $38.25 / 1M characters | — |
| tts-rt-v2Soniox | Not specified | $11.985 / 1M characters | — |
| Inworld TTS-2 FlashInworld AI | Not specified | $12.75 / 1M characters | — |
| audio8DeepInfra | Not specified | $4.25 / 1M characters | — |
