Voxtral Mini 4B Realtime is Mistral AI's language model. A compact 4B-parameter real-time speech and audio language model from Mistral, optimized for low-latency voice interactions.
Specifications
Canonical IDmistral-voxtral-mini-4b-realtime
TypeLanguage
StatusActive
CreatorMistral AIMistral AI
Input ModalitiesText
Output ModalitiesText
Parameters4B

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·

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Voxtral Mini 3B128K$0.040$0.040Available
Voxtral Small 24B128K$0.100$0.300Available
Voxtral Mini 4B RealtimeCurrent
Voxtral Mini Transcribe Realtime$0.006Available
Voxtral Mini TTS$0.000$16.00Available
Voxtral TTSAvailable

Model IDs

huggingface-asr-voxtral-mini-4b-realtime-2602
mistral-voxtral-mini-4b-realtime