Voxtral Mini Transcribe Realtime 2 is a speech-to-text model by Mistral. On Nodion you stream audio to it over the AI Gateway's realtime WebSocket with the model id mistral/voxtral-mini-transcribe-realtime.
One endpoint in front of every provider, operated in the EU.
Prices in EUR excl. VAT
mistral/voxtral-mini-transcribe-realtimeCall it
wss://api.nodion.ai/v1/audio/transcriptions/realtime?model=mistral/voxtral-mini-transcribe-realtime with the same bearer key. The wire format is Mistral's JSON frames (session.update, input_audio.append with base64 PCM), not OpenAI's realtime API. Details are in the AI Inference docs.
Every provider on the gateway is an EU provider with zero data retention. In your project's AI settings you can also restrict which providers and regions may serve requests. Details are in the AI Inference docs.
More models
In the EU, in datacenters in France according to the catalog.
No. Every provider on the Nodion AI Gateway runs with zero data retention and does not store your prompts or outputs.
Billing is per audio minute. The current price is at the top of this page; you pay from a prepaid wallet.
Over the realtime WebSocket wss://api.nodion.ai/v1/audio/transcriptions/realtime?model=mistral/voxtral-mini-transcribe-realtime with an API key from the dashboard.
Earn up to 15 € in credit when signing up.
or with email
Product news, no spam. Unsubscribe anytime.
Successfully subscribed.