Compare realtime APIs
Pick up to four APIs from any category and see them side by side.
| Voxist ASR (via OVHcloud / Scaleway marketplaces) Voxist | ElevenLabs Scribe v2 Realtime ElevenLabs | Mistral Voxtral Mini Transcribe Realtime Mistral AI | |
|---|---|---|---|
| Category | Speech-to-text | Speech-to-text | Speech-to-text |
| Status | GA | GA | GA |
| Est. per minute | $0.0063 - 0.016 | $0.0065 - 0.0098 | $0.006 |
| How that was worked out | Licence EUR 0.35-0.88/hr (~$0.006-0.016/min at ~1.1 USD/EUR) before GPU compute. Low confidence. | $0.39/hr base to $0.59/hr with keyterms + editing. | Flat announced rate; not confirmed on a live pricing table in this pass. |
| Pricing model | per-hour | per-hour | per-minute |
| Free tier | None stated. | Free plan includes about 2.5 realtime hours. | Not stated. |
| Connects by | WebSocket, REST | WebSocket | WebSocket |
| Audio in | WAV, mono only; examples use 16 kHz. | audio_format: pcm_8000, pcm_16000 (default), pcm_22050, pcm_24000, pcm_44100, pcm_48000, ulaw_8000; audio sent base64 in JSON input_audio_chunk messages. | AudioFormat(encoding='pcm_s16le', sample_rate=16000) in docs examples; mic example sends 480 ms chunks. |
| Audio out | n/a | n/a | n/a |
| Languages | Not listed on the billing page (examples show en and French output). | 90+ languages (vendor); language_code plus secondary_languages hints. | 13 languages (vendor). |
| Latency (vendor claim) | Not captured. | Vendor claim: ~150 ms (footnoted, conditions not stated). | Vendor claim: configurable latency down to sub-200 ms; press reports ~1-2% error rate at 480 ms delay (secondary source). |
| Key limits |
|
|
|
| High-severity warnings |
|
|
|
| Compliance | Runs in your own cloud project; certifications not checked. | Data-residency hosts for EU, India, Singapore; enable_logging=false for zero retention. Certifications not re-verified. | Not re-verified. Self-hosting keeps audio fully in your infrastructure. |
| Self-hostable | Yes | No | Yes |
| Last checked | 2026-10-10 | 2026-10-10 | 2026-10-10 |
| Key numbers and features | |||
| $/hour | - | $0.39 | $0.36 |
| Bills silence | - | - | - |
| Free tier | - | Yes | - |
| Free credit $ | - | - | - |
| Live speakers | No | - | No |
| Turn detect | - | Yes | - |
| Keyterms | - | Yes | - |
| PII redact | - | - | - |
| Partials | - | Yes | Yes |
| Mixed langs | - | - | - |
| 8 kHz phone | No | Yes | - |
| Latency ms | - | 150 | 200 |
| Languages | - | 90 | 13 |
| Max session min | - | - | - |
| Concurrency | - | 9 | - |
| WebRTC | No | No | No |
| WebSocket | Yes | Yes | Yes |
| gRPC | No | No | No |
| HIPAA | - | - | - |
| SOC 2 | - | - | - |
| EU data | Yes | Yes | - |
| Self-host | Yes | No | Yes |
| Open weights | No | No | Yes |
| High warnings | 0 | 0 | 0 |