Voxist ASR (via OVHcloud / Scaleway marketplaces)
French ASR vendor sold through OVHcloud AI Deploy and Scaleway marketplaces: a REST API with diarization and a WebSocket streaming API without diarization, licence billed per audio hour plus your GPU compute.
Overview
Best for: EU sovereign-cloud deployments that want a French vendor running inside their own OVHcloud or Scaleway project.
At a glance
Licence EUR 0.88/hr of audio (first 100K min) plus GPU compute billed separately; the price unit on the OVHcloud page is ambiguous. Runs in your own OVHcloud or Scaleway project (EU clouds). WAV mono only, so mulaw must be converted.
WAV, mono only; examples use 16 kHz.
n/a
Not listed on the billing page (examples show en and French output).
Not captured.
Deployed in your OVHcloud/Scaleway project region (EU clouds); data location not stated on the page.
Runs in your own cloud project; certifications not checked.
Features
- streaming recognition
- punctuation
- diarization (REST only)
Pricing
| What | Price | Unit |
|---|---|---|
| Licence 0-100,000 min | EUR 0.88 | per hour of audio |
| Licence 100,001-500,000 min | EUR 0.67 | per hour of audio |
| Licence 3-6M min | EUR 0.35 | per hour of audio |
| GPU compute (OVHcloud AI Deploy) | e.g. EUR 1.93 | per GPU hour (V100S example) |
Licence EUR 0.35-0.88/hr (~$0.006-0.016/min at ~1.1 USD/EUR) before GPU compute. Low confidence.
Free tier: None stated.
Source: docs.ovhcloud.com
Setup
- Subscribe via OVHcloud AI Ecosystem or Scaleway marketplace.
- Deploy the Voxist app on AI Deploy and wait for RUNNING.
- Use <app_url>/docs for the API; streaming uses the WebSocket guide.
Endpoint
<your AI Deploy app URL> (WebSocket path in Voxist streaming guide)Authentication
Authorization: Bearer <OVHcloud app token> for restricted apps
Warnings
Two bills
You pay the Voxist licence per audio hour plus GPU compute per second for the deployed app, even while idle if the app keeps running.
Unit ambiguity
OVHcloud's page labels the table per hour of audio but its worked examples apply the rates per minute. Get a written quote.
Strict input format
Only WAV mono is accepted; convert telephony mu-law or stereo first.
Plus 12 warnings that apply to all speech-to-text, live APIs. See category warnings.
Limits
- WAV mono only.
- Streaming has no diarization.
Models and products
| Name | Status |
|---|---|
| Voxist ASR (asr-rest:v1.0.9-gpu image for REST) | GA |
Docs and sources
Docs
Sources used
- docs.ovhcloud.com/en/guides/public-cloud/ai-machine-learning/ai-ecosystem-voxis...
- scaleway.com/en/marketplace/catalog/voxist-speech-to-text/
Streaming protocol, language list, latency and the exact price unit.