Typhoon ASR Real-Time
Streaming speech recognition model (114M parameters); accepts wav, mp3, flac, ogg and opus.
Specs
- Context
- —
- Max output
- —
- Input price
- —
- Output price
- —
- Released
- 2025-09-08
Context
- Not published
Pricing
- Not published
Modalities
- Input
- Audio
- Output
- Text
API
- API types
Reasoning
- Not published
Info
- Status
- Active
- Released
- 2025-09-08
- Knowledge cutoff
- —
Features
- Not published
How to call
1 provider
typhoonmodel = typhoon-asr-realtime
JSON
Standard format
{
"id": "typhoon-asr-realtime",
"object": "model",
"created": 1757289600,
"owned_by": "typhoon",
"name": "Typhoon ASR Real-Time",
"api": {
"types": [
"audio"
]
},
"limits": {
"context": null,
"input": null,
"output": null
},
"modalities": {
"input": [
"audio"
],
"output": [
"text"
]
},
"reasoning": {
"supported": null,
"efforts": []
},
"pricing": null,
"features": [],
"info": {
"status": "active",
"release_date": "2025-09-08",
"knowledge_cutoff": null,
"description": "Streaming speech recognition model (114M parameters); accepts wav, mp3, flac, ogg and opus.",
"docs": "https://docs.opentyphoon.ai/en/asr/",
"verified_at": "2026-10-11"
}
}Official sources
2