voxtral-mini-transcribe-realtime-3-0
Voxtral 3 realtime WebSocket transcription with configurable 80-2,400 ms latency, end-of-turn detection, context biasing and diarization.
01 Price
$0.48per hour
Cheaper than 56% of 236 priced speech-to-text and realtime models.
Speech-to-text and realtime $ per hour of audio, log scale 236 priced
other models this modelAll models by price
Pricing source, checked 2026-11-16
02 Languages many
Many languages. Mistral AI doesn't list them individually.
03 Features 3 of 11 listed
- Word timestampsnot listed
- Speaker diarization
- Punctuationnot listed
- Profanity filternot listed
- Custom vocabulary
- Language detection
- Translationnot listed
- Sentimentnot listed
- PII redactionnot listed
- Summarizationnot listed
- Topic detectionnot listed
"Not listed" means the provider's data doesn't mention it, not that the model lacks it.
04 Get this record
curl https://voicedex.dev/v1/providers/mistral/models/voxtral-mini-transcribe-realtime-3-0
Free, no key needed. Use model id voxtral-mini-transcribe-realtime-3-0 with Mistral AI's own API. API reference.