Skip to main content
Watch: I Built an AI App Without Leaving Databricks

Mistral speech APIs - verified

Mistral speech API pricing and models

Mistral: 2 speech-to-text models and 1 text-to-speech model, read from the provider's own pages on October 18, 2026. Its lowest speech-to-text rate converts to $0.18 an hour (Voxtral Mini Transcribe 2). No model here has a scheduled shutdown date.

Read from docs.mistral.ai. Compare every speech API

Speech-to-text
2
Text-to-speech
1
Realtime voice
0
Retiring
0

Voxtral Mini Transcribe 2

Speech-to-text - API id not shown on the provider's pages

Price (provider's unit)

$0.003 /Min (cached $0.0003 /Min)

“| Voxtral Mini Transcribe 2↗ | $0.003 /Min | $0.0003 /Min |”
docs.mistral.ai
Converted $/hour (our arithmetic)
  • $0.18converted from $0.003 per minute
Languages

13 languages

“Supports transcription in 13 languages, including English, Chinese, Hindi, Spanish, Arabic, French, Portuguese, Russian, German, Japanese, Korean, Italian, and Dutch.”
docs.mistral.ai
Streaming

No

“Voxtral Mini Transcribe V2 is designed for batch transcription.”
docs.mistral.ai
Max audio

up to 3 hours per request

“Processes recordings up to 3 hours in a single request.”
docs.mistral.ai
Status
Not stated

Features

  • word-level timestamps

    “Provides precise timestamps for each word, useful for subtitle generation and audio search.”
    docs.mistral.ai
  • context biasing

    “Allows you to guide the model with custom vocabulary for accurate transcription of domain-specific terms.”
    docs.mistral.ai

The API id string was not shown on the fetched pages. Version v26.02.

Voxtral Mini Transcribe Realtime

Speech-to-text - API id not shown on the provider's pages

Price (provider's unit)

$0.006 /Min

“Price USDEUR $0.006 /Min”
docs.mistral.ai
Converted $/hour (our arithmetic)
  • $0.36converted from $0.006 per minute
Languages

13 languages

“Strong performance in 13 languages, ensuring global reach.”
docs.mistral.ai
Streaming

Yes

“Transcribes audio as it arrives, enabling natural and responsive voice interactions.”
docs.mistral.ai
Max audio
Not stated
Status
Not stated

Features

  • configurable latency

    “Configurable latency down to sub-200ms, ideal for voice agents and real-time applications.”
    docs.mistral.ai

Open weights (Apache 2.0). Version v26.02. The model page shows the identifier 'voxtral-mini-transcribe-realtime-2602' followed by a '+1' badge.

Voxtral TTS

Text-to-speech - voxtral-mini-tts-2603

Current
Price (provider's unit)

$16 /M Chars output ($0 /M Chars input)

“| Voxtral TTS↗ | $0 /M Chars | $0 /M Chars | $16 /M Chars |”
docs.mistral.ai
Languages

9 languages

“Supports 9 languages, streaming with ~90ms time-to-first-audio, and no transcript required for voice prompts.”
docs.mistral.ai
Streaming

Yes

“streaming with ~90ms time-to-first-audio”
docs.mistral.ai
Limit per request
Not stated
Status

GA

“March 23, 2026 GACC BY-NC 4.0v26.03”
docs.mistral.ai

Features

  • zero-shot voice cloning

    “Our state-of-the-art text-to-speech model with zero-shot voice cloning.”
    docs.mistral.ai

Weights under CC BY-NC 4.0.

FAQ

How much does Mistral speech-to-text cost?

Voxtral Mini Transcribe 2: $0.003 /Min (cached $0.0003 /Min). Voxtral Mini Transcribe Realtime: $0.006 /Min. Prices are in Mistral's own units as of October 18, 2026.

How much does Mistral text-to-speech cost?

Voxtral TTS: $16 /M Chars output ($0 /M Chars input). Prices are in Mistral's own units as of October 18, 2026.

Sources

Verified from each provider's own pricing pages and model docs; every quote was string-matched against the page that day. Prices are shown in the provider's own unit. Values marked derived were counted by us or taken from Azure's Retail Prices API, not from a pricing page. Prices change without notice; check the linked source before you commit a budget to one.

Newsletter

Know when a speech API changes its prices

One email per week. New model releases, pricing changes and what they mean for what you build.