romtuck/openclaw
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
0a8a1119f8
openclaw/skills/openai-whisper-api/SKILL.md
Glucksberg 0a8a1119f8 docs(skills): update state directory paths to ~/.openclaw 
Update documentation references from legacy paths to the current state
directory structure:

- ~/.clawdbot/ → ~/.openclaw/
- /__moltbot__/canvas/ → /__openclaw__/canvas/

Affected skills:
- canvas: config paths and URL prefix (matches CANVAS_HOST_PATH constant)
- nano-banana-pro: config path
- openai-whisper-api: config path
- session-logs: session log paths
- sherpa-onnx-tts: tool install paths and config
2026-01-30 15:35:19 +00:00

1.1 KiB
Raw Blame History

name description homepage metadata
openai-whisper-api Transcribe audio via OpenAI Audio Transcriptions API (Whisper). https://platform.openai.com/docs/guides/speech-to-text
openclaw
emoji requires primaryEnv
☁️
bins env
curl
OPENAI_API_KEY
OPENAI_API_KEY

OpenAI Whisper API (curl)

Transcribe an audio file via OpenAI’s /v1/audio/transcriptions endpoint.

Quick start

{baseDir}/scripts/transcribe.sh /path/to/audio.m4a

Defaults:

  • Model: whisper-1
  • Output: <input>.txt

Useful flags

{baseDir}/scripts/transcribe.sh /path/to/audio.ogg --model whisper-1 --out /tmp/transcript.txt
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --language en
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --prompt "Speaker names: Peter, Daniel"
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --json --out /tmp/transcript.json

API key

Set OPENAI_API_KEY, or configure it in ~/.openclaw/openclaw.json:

{
  skills: {
    "openai-whisper-api": {
      apiKey: "OPENAI_KEY_HERE"
    }
  }
}