SenseAudio Speech-to-Text Provider

SenseAudio handles speech-to-text for incoming audio and voice-note files using OpenClaw's shared tools.media.audio pipeline. Multipart audio is submitted by OpenClaw to the transcription endpoint that follows OpenAI's API conventions, and whatever text comes back is inserted into the conversation as {{Transcript}} alongside an [Audio] block.

Property	Value
Provider id	`senseaudio`
Plugin	bundled, `enabledByDefault: true`
Contract	`mediaUnderstandingProviders` (audio)
Auth env var	`SENSEAUDIO_API_KEY`
Default model	`senseaudio-asr-pro-1.5-260319`
Default URL	`https://api.senseaudio.cn/v1`
Website	senseaudio.cn
Docs	docs.senseaudio.cn

Getting started

Set your API key

export SENSEAUDIO_API_KEY="..."

Enable the audio provider

{
  tools: {
    media: {
      models: [
        {
          provider: "senseaudio",
          model: "senseaudio-asr-pro-1.5-260319",
          capabilities: ["audio"],
        },
      ],
      audio: {
        enabled: true,
      },
    },
  },
}

Send a voice note

Any connected channel can be used to send an audio message. The audio is uploaded by OpenClaw to SenseAudio, and the resulting transcript feeds into the reply pipeline.

Options

Option	Path	Description
`model`	`tools.media.models[].model`	SenseAudio ASR model id
`language`	`tools.media.models[].language`	Optional language hint
`prompt`	`tools.media.models[].prompt`	Optional transcription prompt
`baseUrl`	`tools.media.models[].baseUrl`	Override the OpenAI-compatible base
`headers`	`tools.media.models[].headers`	Extra request headers

Note

Within OpenClaw, SenseAudio only performs batch STT. For realtime transcription in Voice Call, you still need a provider that supports streaming STT.

Getting started

Set your API key

Enable the audio provider

Send a voice note

Options

Related