Use this file to discover all available pages before exploring further.

SenseAudio

SenseAudio can transcribe inbound audio/voice-note attachments through OpenClaw's shared

text

tools.media.audio

pipeline. OpenClaw posts multipart audio to the OpenAI-compatible transcription endpoint and injects the returned text as

text

{{Transcript}}

plus an

text

[Audio]

block.

Detail	Value
Website	senseaudio.cn
Docs	senseaudio.cn/docs
Auth	text `SENSEAUDIO_API_KEY`
Default model	text `senseaudio-asr-pro-1.5-260319`
Default URL	text `https://api.senseaudio.cn/v1`

Getting Started

```bash} export SENSEAUDIO_API_KEY="..." ```

```json5} { tools: { media: { audio: { enabled: true, models: [{ provider: "senseaudio", model: "senseaudio-asr-pro-1.5-260319" }], }, }, }, } ```

Send an audio message through any connected channel. OpenClaw uploads the audio to SenseAudio and uses the transcript in the reply pipeline.

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

SenseAudio is batch STT only in OpenClaw. Voice Call realtime transcription continues to use providers with streaming STT support.