Transcribe
技能 已验证 活跃Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.
Transcribe audio files to text with optional diarization and known-speaker hints, enabling extraction of speech content from recordings.
功能
- Transcribe audio to text
- Speaker diarization
- Known speaker referencing
- Support for multiple audio formats
- Configurable response formats (text, JSON, diarized_json)
使用场景
- Transcribing meeting recordings to extract key discussion points.
- Converting interviews or podcasts into searchable text documents.
- Labeling speakers in audio content for easier content indexing.
- Extracting spoken text from video files.
非目标
- Performing sentiment analysis on the transcribed text.
- Translating transcribed audio into other languages.
- Real-time transcription (focus is on file-based processing).
- Managing or storing audio files beyond outputting transcripts.
Execution
- info:Pinned dependenciesWhile dependency installation is described, explicit pinning via a lockfile is not evident for the 'openai' library.
安装
npx skills add openai/skills通过 npx 运行 Vercel skills CLI(skills.sh)— 需要本地安装 Node.js,以及至少一个兼容 skills 的智能体(Claude Code、Cursor、Codex 等)。前提是仓库遵循 agentskills.io 格式。
质量评分
已验证类似扩展
Whisper
97OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.
Speech Generation Skill
100Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (`scripts/text_to_speech.py`) with built-in voices and require `OPENAI_API_KEY` for live calls. Custom voice creation is out of scope.
YouTube Downloader
100Download and process YouTube content for research. Use when: downloading competitor videos for analysis; extracting audio for podcasts; getting transcripts for content repurposing; archiving webinars; research content curation
Sheet Music Publisher
99Converts mastered audio to sheet music and creates printable songbooks. Use after mastering when the user wants sheet music or a songbook for their album.
Elevenlabs Stt
98ElevenLabs speech-to-text with Scribe models and forced alignment via inference.sh CLI. Models: Scribe v1/v2 (98%+ accuracy, 90+ languages). Capabilities: transcription, speaker diarization, audio event tagging, word-level timestamps, forced alignment, subtitle generation. Use for: meeting transcription, subtitles, podcast transcripts, lip-sync timing, karaoke. Triggers: elevenlabs stt, elevenlabs transcription, scribe, elevenlabs speech to text, forced alignment, word alignment, subtitle timing, diarization, speaker identification, audio event detection, eleven labs transcribe
Openai Whisper Api
95Transcribe audio via OpenAI Audio Transcriptions API (Whisper).