Soniox stt-rt-v5
Soniox real-time speech-to-text and translation model for live audio across 60+ languages.
Specs
- Context
- —
- Max output
- —
- Input price
- $2/ 1M tokens
- Output price
- $4/ 1M tokens
- Released
- 2026-06-16
Context
- Not published
Pricing · USD / 1M tokens
- Input
- $2
- Output
- $4
- Cache read
- —
- Cache write
- —
Modalities
- Input
- Audio
- Output
- Text
API
- API types
Reasoning
- Not published
Info
- Status
- Active
- Released
- 2026-06-16
- Knowledge cutoff
- —
Features
- Not published
How to call
1 provider
sonioxmodel = stt-rt-v5
realtime
GEThttps://stt-rt.soniox.com/transcribe-websocket
JSON
Standard format
{
"id": "stt-rt-v5",
"object": "model",
"created": 1781568000,
"owned_by": "soniox",
"name": "Soniox stt-rt-v5",
"api": {
"types": [
"realtime"
]
},
"limits": {
"context": null,
"input": null,
"output": null
},
"modalities": {
"input": [
"audio"
],
"output": [
"text"
]
},
"reasoning": {
"supported": null,
"efforts": []
},
"pricing": {
"currency": "USD",
"unit": "1M_tokens",
"input": 2,
"output": 4,
"cache_read": null,
"cache_write": null
},
"features": [],
"info": {
"status": "active",
"release_date": "2026-06-16",
"knowledge_cutoff": null,
"description": "Soniox real-time speech-to-text and translation model for live audio across 60+ languages.",
"docs": "https://soniox.com/docs/stt/models",
"verified_at": "2026-10-11"
}
}Official sources
3