OpenClaw LaunchOpenClaw Launch
tool

faster-whisper

Transcribes OpenClaw or Hermes voice messages with CPU int8 and the lightweight base model.

Install in ToolsView on GitHub ↗

What it provides

Speech to textVoice messagesLightweight connector

Supports OpenClaw and Hermes. The model runs on the shared speech server and audio is uploaded there for processing; user instances install only a lightweight connector, avoiding hundreds of MB of model storage and transcription CPU/RAM.

Where to add it

Open Dashboard Tools, select a running OpenClaw or Hermes instance, then use the card’s Install or Connect action. External services may require an HTTPS endpoint and credentials; the dashboard shows those fields before anything is saved.

Related Speech, video & media

yt-dlpLets bots extract media metadata, subtitles, audio, or video from supported sites into the workspace.OpenMontageTurns outlines, data, and scene plans into 1080p H.264 MP4 videos.FunASRChinese and multilingual speech recognition with timestamp-capable output.