Models/Mistral AI/Voxtral Realtime

Voxtral Realtime

Mistral AI 📝 Transcription

Real-time streaming transcription with 240ms latency. 4B params, 13 languages, Apache 2.0.

Specifications

Speed●●●●● Very Fast
ModalitiesInput: audio  ·  Output: text
FeaturesTools: No Streaming: No

Pricing

Included with plan

Use Voxtral Realtime on Zubnet →

More from Mistral AI

Voxtral Transcribe
Mistral's speech-to-text model for accurate audio transcription.
📝 Transcription
Mistral Large 3
Open-weight flagship. 675B MoE (41B active), multimodal with vision. Apache 2.0 licensed.
🧠 Language Model
Mistral Small
Fast and efficient model for simple tasks. Great balance of performance and cost.
🧠 Language Model
Codestral
Specialized model for code generation, completion, and understanding.
🧠 Language Model