eachlabs-voice-audio
由 eftalyurtseven 提供
Speech & Transcription简介
TTS, STT, voice conversion using ElevenLabs, Whisper, RVC.
描述
该技能的功能
Provides access to text-to-speech, speech-to-text, voice conversion, and audio processing through the EachLabs Predictions API. Supports ElevenLabs TTS and transcription models, Whisper-based transcription with speaker diarization, RVC voice conversion, and audio/video utilities. Authentication requires a single API key.
Consolidates over 30 voice and audio models behind a single API key and uniform prediction flow, removing the need to manage separate credentials and SDKs for ElevenLabs, Whisper, RVC, and Stable Audio.
何时使用
- Transcribe a recorded meeting and label each speaker
- Convert a script to spoken audio using a custom voice
- Dub a video into a different voice or language
- Generate sound effects from a text description
- Merge a narration audio track with a silent video file
示例工作流
User asks: transcribe this meeting recording and identify who is speaking
- 1
Check the whisper-diarization model schema via GET /v1/model?slug=whisper-diarization
- 2
POST to /v1/prediction with the audio file URL, num_speakers, and language set to en
- 3
Poll GET /v1/prediction/{id} until status is success
- 4
Extract the grouped transcript segments with speaker labels from the response
- 5
Return the labeled transcript to the user
A transcript with each segment attributed to a speaker, e.g. Speaker 1: ... Speaker 2: ...
前置要求
- EACHLABS_API_KEY environment variable
- EachLabs account at eachlabs.ai
安装
clawhub install eftalyurtseven/eachlabs-voice-audio运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。