ElevenLabs Audio

Generate downloadable speech and sound effects, transcribe audio, design and save voices, remove background noise, and manage automatic dubbing through the ElevenLabs API.

The connection retains the historical elevenreader identifier. ElevenReader is a separate reading and listening product; these tools do not access its books, imported documents, or personal library.

Connect

Create an ElevenLabs API key. The key must allow the API operations you plan to use, including user information for connection verification. Existing saved API-key connections remain supported.

Workflows

• Discover a voice with list_voices, inspect compatible models with list_models, then generate downloadable audio with generate_speech.
• Generate previews with design_voice_previews, save the selected ID with create_voice_from_preview, and use the returned saved voice ID for speech.
• Transcribe one audio file or HTTPS cloud-storage URL with speech_to_text.
• Create an automatic dub with create_dubbing, poll get_dubbing, then use download_dubbing_audio. Downloads contain the original automatic result, including video when applicable; Dubbing Studio edits require a different API.
• Use list_history and download_history_audio to retrieve retained audio. History excludes music and sound-effect generations.

text_to_speech, generate_sound_effect, isolate_audio, and design_voice remain available for existing callers and retain their original inline audio outputs. Their descriptions identify the download-focused replacements.

ElevenLabs API key permissions, quotas, supported models and formats, and account entitlements apply. See the API documentation.

License

This integration is licensed under the FSL-1.1.