跳到正文
TakoAPI
返回技能列表

elevenlabs-ai

由 codedao12 提供

Coding Agents & IDEs
947下载量由 clawskills.sh 提供
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

OpenClaw skill for ElevenLabs APIs: text-to-speech, speech-to-speech, realtime speech-to-text, voices/models.

描述

该技能的功能

Covers ElevenLabs API workflows via direct HTTPS calls: text-to-speech, speech-to-speech voice conversion, realtime speech-to-text over WebSocket, and multi-voice dialogue generation. Includes auth patterns, voice/model discovery, and operational safety rules.

Direct HTTPS calls avoid SDK version drift and give full control over payloads, retries, and output format selection.

何时使用

  • Convert a script to narrated audio with a specific voice
  • Clone or convert a speaker's voice in an uploaded audio file
  • Stream live transcription from a microphone feed
  • Generate a two-character dialogue with distinct voices
  • Look up available voice IDs before building a TTS pipeline

示例工作流

输入

User asks: convert this blog post text to MP3 audio using a specific voice

智能体
  1. 1

    Reads elevenlabs-authentication.md to confirm API key header format

  2. 2

    Reads elevenlabs-voices-models.md to retrieve the target voice ID and a compatible model ID

  3. 3

    Reads elevenlabs-text-to-speech.md to construct the POST /v1/text-to-speech/{voice_id} request with the chosen output format

  4. 4

    Applies retry-with-backoff logic and caches voice/model IDs for subsequent calls

  5. 5

    Returns the audio file and the endpoint checklist used

输出

MP3 audio file of the blog post narrated in the selected voice

前置要求

  • ElevenLabs API key (xi-api-key) from elevenlabs.io account

安装

clawhub install codedao12/elevenlabs-ai

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。

链接