Data as of October 20, 2026 · How the score is built
Released Oct 20, 2026N/A contextMistral AI model documentation
Voxtral TTS 3
Decision readingVoxtral TTS 3 is tracked, but not publicly ranked yet. Published speech or voice results from Voxtral 3 launch evaluation appear below. They do not produce a weighted text-model score.
Released Oct 20, 2026 — see all recent releases
Voice benchmark evidence
Voxtral 3 launch evaluation is an owner-defined voice evaluation. Its result stays separate from BenchLM's weighted text-model ranking.
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Base entry
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- voxtral-mini-tts-3-0Mistral AI model documentation
- Context window
- N/A
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not disclosed by the provider
- Availability
- Released October 20, 2026 as a public preview in the Mistral API as `voxtral-mini-tts-3-0`, for batch and realtime speech. The launch post also calls it Voxtral Mini TTS 3 and Voxtral Speech 3. It claims 35+ languages and 50+ dialects; the docs page lists 9 languages, about 90 ms to first audio, 34 emotion tags, and 2 pace tags. Voice presets cover 18 languages, and Pro Voice cloning uses 30 minutes of audio.
- Cloud regions
- Not tracked yet
- Lifecycle
- Current
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing recordMistral AI model documentation
- Self-host
- Weights are not published
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
We track Voxtral TTS 3, but no weighted text-model benchmark result is published on the site yet. This page shows the metadata and separate protocol evidence we can verify now; a BenchLM score will appear only if compatible public evaluations land.
Voxtral TTS 3 is a proprietary model with a N/A context window. No explicit reasoning mode is documented in this profile.
Released October 20, 2026 as a public preview in the Mistral API as `voxtral-mini-tts-3-0`, for batch and realtime speech. The launch post also calls it Voxtral Mini TTS 3 and Voxtral Speech 3. It claims 35+ languages and 50+ dialects; the docs page lists 9 languages, about 90 ms to first audio, 34 emotion tags, and 2 pace tags. Voice presets cover 18 languages, and Pro Voice cloning uses 30 minutes of audio.
Voxtral TTS 3 is a text-to-speech model with voice cloning and controls for emotion, pace, and emphasis. Its speech results stay separate from weighted text-model rankings.
Speech or voice evidence appears above; text-model benchmark coverage remains empty.
Last updated October 20, 2026. Runtime fields remain blank until a sourced snapshot exists.
Questions
How does Voxtral TTS 3 perform overall in AI benchmarks?
Voxtral TTS 3 has published speech or voice results in Voxtral 3 launch evaluation. Those results remain separate from the weighted text-model ranking, so this profile does not assign a BenchLM score or overall rank. Use the linked evaluation's metric and run conditions to compare speech systems.
Does Voxtral TTS 3 have full benchmark coverage on BenchLM?
No. Voxtral TTS 3's speech or voice results appear in Voxtral 3 launch evaluation, but it has no published text-model benchmark rows. The voice evaluation does not fill the text-model coverage slots or produce an overall rank. Missing text coverage is not treated as a zero score.
What is the context window size of Voxtral TTS 3?
Voxtral TTS 3 has a reported context window of N/A in the exact-model catalog record. The value stays visible, but the profile marks its source link as unavailable instead of presenting it as directly documented. Maximum output length remains separate because providers often publish a different limit.