elevenlabs-voices
由 robbyczgw-cla 提供
Speech & Transcription简介
High-quality voice synthesis with 18 personas, 32.
描述
该技能的功能
Voice synthesis toolkit built on the ElevenLabs API with 18 curated personas covering multiple accents and use cases. Supports 32 languages, real-time streaming, batch processing, AI-generated sound effects, and custom voice design from text descriptions.
The 18 pre-tuned personas with optimized stability and style settings remove the need to manually calibrate ElevenLabs voice parameters for common output types.
何时使用
- Converting articles or documentation into MP3 audio files
- Generating multilingual voiceovers for videos or presentations
- Batch-narrating audiobook chapters with consistent voice settings
- Creating ambient or event sound effects from text prompts
- Producing branded podcast intros with a custom-designed voice
示例工作流
User asks: Read this blog post aloud using the narrator preset and save it as post.mp3
- 1
Runs tts.py --list to confirm available presets and voices
- 2
Selects the narrator preset, which maps to the adam voice
- 3
Calls tts.py --text "<post content>" --voice narrator --output post.mp3
- 4
Runs tts.py --stats to show character usage and estimated cost
post.mp3 file narrated in adam's voice, with character count and cost estimate printed to terminal
前置要求
- ELEVEN_API_KEY environment variable
- ElevenLabs account at elevenlabs.io
安装
clawhub install robbyczgw-cla/elevenlabs-voices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。