← ClaudeAtlas

elevenlabslisted

Generate realistic speech with the ElevenLabs API and its Python and Node.js SDKs. Use when a user asks to convert text to speech, stream audio, clone a voice, pick a TTS model, or build a voice agent with ElevenLabs.
trku052-png/social-media-youtube-skills · ★ 1 · AI & Automation · score 68
Install: claude install-skill trku052-png/social-media-youtube-skills
# ElevenLabs — AI Voice Synthesis & Cloning ## Overview ElevenLabs is a hosted voice platform: text-to-speech, speech-to-text, voice cloning and a managed conversational agent product. You call it with an API key through the official SDKs (`elevenlabs` on PyPI, `@elevenlabs/elevenlabs-js` on npm) or plain HTTP. Checked against elevenlabs 2.70.0 (Python, 28 Sep 2026) and the current models page. Two things changed since many tutorials were written: `convert_as_stream` no longer exists (use `text_to_speech.stream`), and the old npm package `elevenlabs` is deprecated in favour of `@elevenlabs/elevenlabs-js`. ## Instructions ### Step 1: Install and authenticate ```bash pip install elevenlabs # Python npm install @elevenlabs/elevenlabs-js # Node.js (the unscoped "elevenlabs" package is deprecated) export ELEVENLABS_API_KEY="..." # create it in the dashboard; never commit it ``` ### Step 2: Text to speech ```python import os from elevenlabs.client import ElevenLabs from elevenlabs import VoiceSettings client = ElevenLabs(api_key=os.environ["ELEVENLABS_API_KEY"]) # find a voice id available to your account for v in client.voices.search(search="narrator").voices: print(v.voice_id, v.name) audio = client.text_to_speech.convert( voice_id="JBFqnCBsd6RMkjVDRZzb", text="Welcome to Bright Smile Dental. How can I help you today?", model_id="eleven_flash_v2_5", output_format="mp3_44100_128", voice_settings=VoiceSetti