Openai Whisper
OpenAI Whisper:使用 Whisper 模型进行视频语音识别和转录。
clawhub install openai-whisperTranscribe videos and perform speaker diarization on audio content
# Install Skill (downloads SKILL.md to .claude/skills/) clawhub install moss-transcribe-diarize # Then just tell Claude: "use moss-transcribe-diarize to help me..."
# Same install command — works with all SKILL.md-compatible AI coding tools clawhub install moss-transcribe-diarize
This Skill is compatible with the OpenClaw standard. After installation, a SKILL.md file is auto-generated, usable by any OpenClaw-compatible AI Agent (Claude Code, Cursor, Windsurf, etc.).
scripts/transcribe.py。python scripts/transcribe.py --audio-url "https://example.com/audio.mp3" --out "result.json"
python scripts/transcribe.py --file "/path/to/meeting.mp4" --out "result.json"
python scripts/transcribe.py --audio-data "data:audio/wav;base64,..." --out "result.json"
--segments-format text
- JSON 数组(推荐,含 speaker):--segments-format json
- 紧凑 JSON 串:--segments-format compactMOSS_API_KEY → MOSI_TTS_API_KEY → MOSI_API_KEY。如果都缺失,请提醒用户。moss-transcribe-diarize。https://studio.mosi.cn/v1/audio/transcriptions(不再暴露自定义 endpoint 参数)。*.json:原始响应
- *.segments.*:分段结果(格式由 --segments-format 决定,含 speaker)
- *.by_speaker.txt:按说话人汇总clawhub moss-transcribe-diarize --input conference.mp4 --output result.json --diarize true --language auto