Voxtral Mini Transcribe Realtime 3 is Mistral AI's speech to text model. A low-latency multilingual transcription model built for real-time audio streaming with speaker diarization support.
Specifications
Canonical IDmistral-voxtral-3-mini-transcribe-realtime
TypeSpeech to Text
StatusActive
CreatorMistral AIMistral AI
Providers
Input ModalitiesAudio
Output ModalitiesText

Capabilities

Input1/5
Text·
Image·
Audio✓
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Audio In
$ / sec
Mistral AI logo
Mistral AI
mistral/voxtral-mini-transcribe-realtime-3
$0.000133

Cost Calculator

US Dollar ($)
Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Voxtral Mini Transcribe 332K——Available
Voxtral Small Transcribe 332K——Available
Voxtral TTS 3—$16.00—Available
Voxtral Mini Transcribe Realtime 3————Current
Voxtral 3 TTS————Available
Voxtral Mini TTS Realtime 3————Available
Voxtral Mini 3B128K$0.040$0.040Deprecating
Voxtral Small 24B128K$0.100$0.300Deprecated
Voxtral Mini 4B Realtime————Available
Voxtral Mini Realtime————Available
Voxtral Mini Transcribe————Available

Model IDs

mistral-voxtral-3-mini-transcribe-realtime
mistral/voxtral-mini-transcribe-realtime-3
mistral/voxtral-mini-transcribe-realtime-3-0
voxtral-mini-transcribe-realtime-3
voxtral-mini-transcribe-realtime-3-0