ModelInfo
English
All models

SenseAudio-Realtime-1.0

End-to-end real-time speech dialogue model over WebSocket.

SenseTimesenseaudio-realtime-1.0Report incorrect data

Specs

Context
—
Max output
—
Input price
¥0.6/ minute
Output price
—
Released
—

Context

Not published

Pricing · CNY / minute

Input
¥0.6
Output
—
Cache read
—
Cache write
—

Modalities

Input
Audio
Output
TextAudio

API

API types
realtime

Reasoning

Not published

Info

Status
Active
Released
—
Knowledge cutoff
—

Features

Confirmed
toolsstreaming
Source · official docsVerified 2026-10-11

How to call

1 provider

senseaudiomodel = senseaudio-realtime-1.0

JSON

Standard format
senseaudio-realtime-1.0.json
{
  "id": "senseaudio-realtime-1.0",
  "object": "model",
  "created": null,
  "owned_by": "sensetime",
  "name": "SenseAudio-Realtime-1.0",
  "api": {
    "types": [
      "realtime"
    ]
  },
  "limits": {
    "context": null,
    "input": null,
    "output": null
  },
  "modalities": {
    "input": [
      "audio"
    ],
    "output": [
      "text",
      "audio"
    ]
  },
  "reasoning": {
    "supported": null,
    "efforts": []
  },
  "pricing": {
    "currency": "CNY",
    "unit": "minute",
    "input": 0.6,
    "output": null,
    "cache_read": null,
    "cache_write": null
  },
  "features": [
    "tools",
    "streaming"
  ],
  "info": {
    "status": "active",
    "release_date": null,
    "knowledge_cutoff": null,
    "description": "End-to-end real-time speech dialogue model over WebSocket.",
    "docs": "https://docs.senseaudio.cn/guides/agent/overview",
    "verified_at": "2026-10-11"
  }
}

Official sources

2