ElevenLabs

Generate a spoken audio file from any text input using an ElevenLabs AI voice model and a selected voice.

Generate an audio file with word-level timestamp alignment — useful for subtitle generation or precisely timed audio playback.

Create a custom cloned voice from one or more audio samples so agents can generate speech that consistently matches a specific person or brand voice.

Convert an audio file into text using ElevenLabs Scribe — the high-accuracy speech-to-text engine that returns a full transcript with speaker diarisation and timestamps.

Translate and re-voice a video or audio file into a target language while preserving speaker timing and voice characteristics.

Check the progress and status of an in-flight dubbing project by its ID — useful for polling long-running dubbing jobs before downstream steps consume the output.

Create a custom sound effect audio clip from a text prompt using ElevenLabs' sound effects model.

Process an audio file through ElevenLabs' audio isolation model to remove background noise and extract a clean vocal or instrument track.

Retrieve all available voices in the connected ElevenLabs account, including pre-made and cloned voices with their IDs, languages, and settings.

Retrieve metadata and settings for a specific voice by ID, including its name, labels, description, and fine-tuning parameters.

Permanently remove a cloned or personal voice from the ElevenLabs account by its voice ID.

List all available speech synthesis models in ElevenLabs, including their IDs, languages, and capability flags, so agents can choose the best model for each use case.

Retrieve the current billing period's character usage and remaining quota for the connected ElevenLabs account — useful for cost monitoring and rate-limit guardrails.

Retrieve metadata and audio download URL for a previously generated TTS history item by its ID.

Remove a generated audio history item from the ElevenLabs account to maintain privacy, manage storage, or clean up after content review.