SenseAudio Batch Speech-to-Text for Inbound Voice Notes

This page covers SenseAudio, a batch speech-to-text provider for inbound audio and voice-note attachments. It explains how OpenClaw transcribes audio using the SenseAudio API and inserts the transcript into replies.

Read this when

  • You want SenseAudio speech-to-text for audio attachments
  • You need the SenseAudio API key env var or audio config path

SenseAudio transcribes inbound audio and voice-note attachments using OpenClaw's shared tools.media.audio pipeline. OpenClaw sends multipart audio to the OpenAI-compatible transcription endpoint and inserts the returned text as {{Transcript}} plus an [Audio] block.

PropertyValue
Provider idsenseaudio
Pluginbundled, enabledByDefault: true
ContractmediaUnderstandingProviders (audio)
Auth env varSENSEAUDIO_API_KEY
Default modelsenseaudio-asr-pro-1.5-260319
Default URLhttps://api.senseaudio.cn/v1
Websitesenseaudio.cn
Docssenseaudio.cn/docs

Getting started

Set your API key

export SENSEAUDIO_API_KEY="..."

Enable the audio provider

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

Send a voice note

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

Options

OptionPathDescription
modeltools.media.models[].modelSenseAudio ASR model id
languagetools.media.models[].languageOptional language hint
prompttools.media.models[].promptOptional transcription prompt
baseUrltools.media.models[].baseUrlOverride the OpenAI-compatible base
headerstools.media.models[].headersExtra request headers

Note

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