Install
openclaw skills install whisper-local-apiSecure, offline, OpenAI-compatible local Whisper ASR endpoint for OpenClaw. Features faster-whisper (large-v3-turbo), built-in privacy with no cloud telemetry, low-RAM usage footprint, and high-accuracy speech-to-text transcription. Perfect for safe and private AI agent voice commands.
openclaw skills install whisper-local-apiDeploy a privacy-first, 100% local speech-to-text service in a deterministic way. This allows OpenClaw to process audio transcriptions safely on your own hardware without ever contacting third-party cloud APIs.
large-v3-turbo model via faster-whisper, achieving state-of-the-art accuracy even with accents or background noise./v1/audio/transcriptions endpoint mimicking OpenAI's JSON format. Compatible natively with any software that supports OpenAI's Whisper API.bash scripts/bootstrap.sh
bash scripts/start.sh
bash scripts/healthcheck.sh
bash scripts/smoke-test.sh /path/to/test-speech.mp3
Default install/update path used by scripts:
~/whisper-local-apiOverride with env var before running scripts:
WHISPER_DIR=/custom/path bash scripts/bootstrap.sh
After the healthcheck passes, use the secure local endpoint:
http://localhost:9000/v1/audio/transcriptionsNo authentication tokens are passed over the network.
0.0.0.0. If exposing to the public internet, deploy behind a secure reverse proxy (like Nginx) and enforce HTTPS + Basic Auth.float16 -> int8) to prevent CPU crashes.