Mistral: Voxtral TTS 3

Voxtral TTS 3 is Mistral's text-to-speech model. It converts text into natural-sounding speech, offers a library of preset voices, supports zero-shot voice cloning, and accepts emotion and pace tags …

mistralai/voxtral-mini-tts-3-0-20261020

Voxtral TTS 3 is Mistral's text-to-speech model. It converts text into natural-sounding speech, offers a library of preset voices, supports zero-shot voice cloning, and accepts emotion and pace tags in the input to control delivery. It streams audio with low time-to-first-audio and suits voice agents, narration, and multilingual assistants.

Specifications & capabilities

Input
text
Output
speech
Context window · tokens
4096
Supported voices
voice_3150, voice_478, voice_447, voice_485, en_paul_sad, en_paul_neutral, en_paul_happy, en_paul_frustrated, en_paul_excited, en_paul_confident, en_paul_cheerful, en_paul_angry, voice_3149, voice_3147, voice_591, voice_590, voice_1788, voice_1787, voice_1786, gb_oliver_neutral, gb_jane_sarcasm, gb_jane_confused, gb_oliver_sad, gb_oliver_excited, gb_oliver_curious, gb_oliver_confident, gb_oliver_cheerful, gb_oliver_angry, gb_jane_shameful, gb_jane_sad, gb_jane_neutral, gb_jane_jealousy, gb_jane_frustrated, gb_jane_curious, gb_jane_confident, voice_479, voice_3143, voice_481, voice_483, voice_592, voice_3137, voice_589, voice_3141, fr_marie_sad, fr_marie_neutral, fr_marie_happy, fr_marie_excited, fr_marie_curious, fr_marie_angry, voice_3153, voice_3139, voice_3146, voice_482, voice_3133, voice_3136, voice_3135, voice_3145, voice_3134, voice_3154, voice_480, voice_3155, voice_3132, voice_3138, voice_3140, voice_3144, voice_3142
Published model ID
voxtral-mini-tts-3-0
Capabilities
audioInput, multimodal, speechOutput, streaming, voiceCloning
Description source ↗

Published prices

1–2 / 2

voxtral-mini-tts-3-0 ↗

$13.00

Inference provider
mistral
Platform
Mistral
Unit
input_characters_per_million
Currency
USD
Billing conditions
Billing label
input / 1M characters

mistralai/voxtral-mini-tts-3-0 ↗

$0.000013

Inference provider
openRouter
Platform
OpenRouter
Unit
catalog_quote
Currency
USD
Billing conditions
raw_field
prompt
billing_unit_status
unverified
Billing label
Published scalar; billing unit unverified

Provider specifications & access

1–2 / 2

voxtral-mini-tts-3 ↗

source model id
voxtral-mini-tts-3
hosting
gateway
platforms
  • Cheaper Inference
architecture
input_modalities
    output_modalities
    • audio
    capabilities

      Voxtral TTS 3 ↗

      source model id
      voxtral-mini-tts-3-0
      hosting
      mistral-hosted
      platforms
      • Mistral
      architecture
      input_modalities
      • text
      • audio
      output_modalities
      • speech
      capabilities
      • speechOutput
      • streaming
      • voiceCloning

      Safety assessments

      1–1 / 1

      Foundation Model Transparency Index 2025 ↗

      18 / 100

      source id
      stanfordFMTI
      canonical model id
      mistralai/voxtral-mini-tts-3-0-20261020
      taxonomy
      transparency
      hazard category
      transparency
      hazard name
      Organization transparency
      policy area
      Mistral
      assessment type
      organization-level disclosure
      metric
      disclosure_score
      result label
      18 / 100
      sample size
      100
      updated at
      2026-11-09T18:08:05.227Z

      Source specification observations

      1–2 / 2

      openRouter ↗

      field
      context_length
      value
      4096
      normalized value
      4096
      scope
      source-model
      source id
      openRouter
      confidence
      1

      openRouter ↗

      field
      max_output_tokens
      value
      3276
      normalized value
      3276
      scope
      source-model
      source id
      openRouter
      confidence
      1

      Original sources

      1–6 / 6

      OpenRouter · Model page ↗

      Mistral AI · Model documentation ↗

      api.cheaperinference.com · Source snapshot ↗

      GitHub · Catalog ↗

      Mistral AI · Catalog ↗

      OpenRouter · Catalog ↗

      Source links

      1–4 / 4

      Explore more models

      Models

      Loading
      EVIDENCE / COMPARISON

      Benchmarks

      Explore every benchmark

      Loading

      These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

      Install TensorTrace