# ElevenLabs integration

> Generate lifelike speech from text, clone voices, transcribe audio, and produce sound effects with ElevenLabs' AI audio models.

- Authentication: apiKey

## Tools (52)

- **Add Pronunciation Dictionary From File**: Upload a PLS (Pronunciation Lexicon Specification) file to create a new dictionary.
- **Add Shared Voice to Library**: Add a voice from the public library to your personal voice library.
- **Add Voice (Instant Voice Clone)**: Create a new cloned voice from audio sample files.
- **Audio Isolation**: Remove background noise/music from a recording, leaving only the speech.
- **Compose Music**: Compose a full music track from a text prompt or a composition plan.
- **Compose Music with Details**: Compose a music track and return the audio together with its composition plan, metadata, and song id.
- **Create Conversational AI Agent**: Create a new conversational voice agent with prompt, voice, and tools.
- **Create Dubbing Job**: Translate and dub an audio or video file into one or more target languages.
- **Create Music Composition Plan**: Generate a structured composition plan from a prompt to steer subsequent music generation.
- **Create Studio Project**: Create a long-form Studio project from text, a document, or a URL.
- **Delete Conversational AI Agent**: Delete a conversational AI agent.
- **Delete Dubbing Project**: Delete a dubbing project and its outputs.
- **Delete History Item**: Permanently delete a single item from generation history.
- **Delete Voice**: Delete a cloned voice from your library.
- **Design Voice (Text to Voice Preview)**: Generate candidate voice previews from a text description of the target speaker.
- **Download History Items (Batch)**: Download multiple history items as a single zip archive.
- **Edit Voice**: Update an existing cloned voice's name, description, labels, or sample files.
- **Edit Voice Settings**: Update the default synthesis settings stored on a voice.
- **Forced Alignment**: Align a text transcript to its audio with per-word and per-character timestamps.
- **Get Conversation**: Retrieve a full conversation transcript and metadata by id.
- **Get Conversational AI Agent**: Retrieve a conversational AI agent's full configuration.
- **Get Conversational AI Signed URL**: Mint a short-lived signed WebSocket URL for connecting a client to a voice agent.
- **Get Conversation Audio**: Download the recorded audio for a conversation.
- **Get Default Voice Settings**: Get the platform default voice synthesis settings.
- **Get Dubbed Audio**: Download the dubbed audio or video file in a target language.
- **Get Dubbing Project**: Poll the status of a dubbing job and read its metadata.
- **Get Dubbing Transcript**: Retrieve the timed transcript (SRT/WebVTT) for a dubbing project's target language.
- **Get History Item Audio**: Download the audio file for a generated history item.
- **Get Shared Voices (Public Voice Library)**: Browse the public ElevenLabs voice library shared by other creators.
- **Get Subscription**: Get the authenticated user's current subscription, quota, and limits.
- **Get User**: Get information about the authenticated user, including subscription tier.
- **Get Voice**: Retrieve a single voice by id, including settings, samples, and sharing metadata.
- **Get Voice Settings**: Get the saved synthesis settings for a specific voice.
- **List Conversational AI Agents**: List conversational AI agents in your workspace.
- **List Conversations**: List past conversations with conversational AI agents.
- **List History**: List generated audio items in your account history with cursor pagination.
- **List Models**: List all available TTS, STS, and STT models with their capabilities and supported languages.
- **List Pronunciation Dictionaries**: List the pronunciation dictionaries available to your workspace.
- **List Voices**: List all voices available to the account, including premade, cloned, and shared voices.
- **Save Designed Voice**: Persist a designed voice preview into your voice library.
- **Search Voices (v2)**: Paginated, searchable list of voices with filtering by category and sort options.
- **Sound Effect Generation**: Generate a sound effect or ambience clip from a text prompt.
- **Speech to Speech**: Convert speech audio into the voice of another speaker while preserving timing and emotion.
- **Speech to Text (Transcribe)**: Transcribe an audio or video file into text with optional speaker diarization.
- **Stream Music**: Compose a music track and stream the audio as it is generated.
- **Stream Music with Details**: Compose a music track and stream audio chunks alongside the composition plan and metadata.
- **Stream Text to Speech**: Convert text to speech and stream the audio as it is generated.
- **Text to Speech**: Convert text into speech audio using a chosen voice and model.
- **Update Conversational AI Agent**: Update an existing conversational AI agent's configuration.
- **Upload Music**: Upload an existing audio file to register a song, optionally extracting a composition plan and word timestamps.
- **Video to Music**: Generate a music track scored to one or more uploaded video clips.
- **Workspace Usage Metrics**: Get character usage metrics over a time range, broken down by voice/model/user.

## Related prompts

- [Send a personalized voicemail to every new HubSpot lead](https://www.generalinput.com/prompts/send-a-personalized-voicemail-to-every-new-hubspot-lead.md)
- [Narrate every new Ghost blog post into an audio edition](https://www.generalinput.com/prompts/narrate-every-new-ghost-blog-post-into-an-audio-edition.md)
- [Auto-log sales call recordings from Google Drive to HubSpot](https://www.generalinput.com/prompts/auto-log-sales-call-recordings-from-google-drive-to-hubspot.md)
- [Daily team briefing in Slack with a voice recording](https://www.generalinput.com/prompts/daily-team-briefing-in-slack-with-a-voice-recording.md)
- [Turn every Granola meeting into a 90-second Slack audio recap](https://www.generalinput.com/prompts/turn-every-granola-meeting-into-a-90-second-slack-audio-recap.md)

Connect ElevenLabs in General Input: https://www.generalinput.com/apps/elevenlabs