MeetingMind Voxtral Transcription Endpoint

GPU-accelerated speech-to-text for the MeetingMind pipeline using Voxtral Realtime 4B. Runs as an HF Inference Endpoint on a T4 GPU with scale-to-zero.

Model weights: mistral-hackaton-2026/voxtral_model — Voxtral Realtime 4B (BF16 safetensors, loaded from /repository/voxtral-model/)

API

`GET /health`

Returns service status and GPU availability.

curl -H "Authorization: Bearer $HF_TOKEN" $ENDPOINT_URL/health

{"status": "ok", "gpu_available": true}

`POST /transcribe`

Speech-to-text using Voxtral Realtime 4B. Returns full transcription.

curl -X POST \
  -H "Authorization: Bearer $HF_TOKEN" \
  -F audio=@speech.wav \
  $ENDPOINT_URL/transcribe

{"text": "Hello, this is a test of the voxtral speech to text system."}

`POST /transcribe/stream`

Streaming speech-to-text via SSE. Tokens are emitted as they are generated.

curl -X POST \
  -H "Authorization: Bearer $HF_TOKEN" \
  -F audio=@speech.wav \
  $ENDPOINT_URL/transcribe/stream

Events: token (partial), done (final text), error.

Environment Variables

Variable	Default	Description
`VOXTRAL_MODEL_DIR`	`/repository/voxtral-model`	Path to Voxtral model weights

Architecture

Base image: pytorch/pytorch:2.4.0-cuda12.4-cudnn9-runtime
Transcription: Voxtral Realtime 4B via direct safetensors loading (~8GB VRAM)
Scale-to-zero: 15 min idle timeout (~$0.60/hr when active)
Diarization & embeddings: Served separately by the GPU service on machine "tanti"

Downloads last month: -; Downloads are not tracked for this model. How to track