ElevenLabs

List all voices available to the authenticated account (GET /voices).

Get metadata for a single voice (GET /voices/{voice_id}).

Get the platform default voice settings (GET /voices/settings/default).

Get the settings for a specific voice (GET /voices/{voice_id}/settings).

Update the settings for a voice (POST /voices/{voice_id}/settings/edit).

Create a new instant voice clone from one or more audio samples (POST /voices/add). Multipart upload; returns the new voice_id.

Edit an existing voice's name, samples, or metadata (POST /voices/{voice_id}/edit). Multipart upload.

Delete a voice from the account (DELETE /voices/{voice_id}).

Download the audio for a specific voice sample (GET /voices/{voice_id}/samples/{sample_id}/audio). The response body is binary audio.

Delete a single sample from a voice (DELETE /voices/{voice_id}/samples/{sample_id}).

Add a public Voice Library voice to your account (POST /voices/add/{public_user_id}/{voice_id}).

List Studio projects in the account (GET /projects).

Get a Studio project's metadata (GET /projects/{project_id}).

Create a new Studio project (POST /projects/add). Multipart upload of source content plus settings.

Delete a Studio project (DELETE /projects/{project_id}).

Start converting (rendering) a Studio project to audio (POST /projects/{project_id}/convert).

List the rendered snapshots of a Studio project (GET /projects/{project_id}/snapshots).

Stream the audio of a project snapshot (POST /projects/{project_id}/snapshots/{project_snapshot_id}/stream). The response body is a binary audio stream.

Set the pronunciation dictionaries applied to a Studio project (POST /projects/{project_id}/pronunciation-dictionaries).

Create a pronunciation dictionary from a rules file (POST /pronunciation-dictionaries/add-from-file). Multipart upload.

Create a pronunciation dictionary from inline rules (POST /pronunciation-dictionaries/add-from-rules).

List pronunciation dictionaries in the account (GET /pronunciation-dictionaries).

Get a pronunciation dictionary's metadata (GET /pronunciation-dictionaries/{pronunciation_dictionary_id}).

Remove rules from a pronunciation dictionary (POST /pronunciation-dictionaries/{pronunciation_dictionary_id}/remove-rules).

Download a pronunciation dictionary version as a PLS file (GET /pronunciation-dictionaries/{dictionary_id}/{version_id}/download). The response body is a text/PLS file.

Dub an audio/video file or URL into a target language (POST /dubbing). Multipart upload; returns a dubbing_id to poll.

Get the status and metadata of a dubbing job (GET /dubbing/{dubbing_id}).

Delete a dubbing job (DELETE /dubbing/{dubbing_id}).

Download the dubbed audio/video for a language (GET /dubbing/{dubbing_id}/audio/{language_code}). The response body is binary media.

Get the transcript for a dubbing job in a language (GET /dubbing/{dubbing_id}/transcript/{language_code}).

List generated audio history items with cursor pagination (GET /history). Recommended polling action for new generations.

Get a single generation history item's metadata (GET /history/{history_item_id}).

Delete a single generation history item (DELETE /history/{history_item_id}).

Download the audio for a generation history item (GET /history/{history_item_id}/audio). The response body is binary audio.

Download one or more history items as audio, zipped when multiple (POST /history/download). The response body is binary (audio or zip).

Get the authenticated user's workspace, including groups (GET /workspace). Used to inspect workspace members and groups.

Invite a user to the workspace by email (POST /workspace/invites/add).

Remove a member from the workspace (DELETE /workspace/members).

Add or remove members of a workspace group (POST /workspace/groups/{group_id}/members).

Convert text to speech with a chosen voice (POST /text-to-speech/{voice_id}). The response body is binary audio (default audio/mpeg).

Stream synthesized speech as it is generated (POST /text-to-speech/{voice_id}/stream). The response body is a binary audio stream.

Convert text to speech and return base64 audio plus per-character alignment timestamps (POST /text-to-speech/{voice_id}/with-timestamps). Response is JSON: audio_base64 + alignment.

Create an Audio Native player project and get its embed snippet (POST /audio-native). Multipart upload.

Update the content of an Audio Native project (POST /audio-native/{project_id}/content). Multipart upload.

Design a new voice from a text description and generate preview audios (POST /text-to-voice/create-previews).

Save a generated preview as a permanent voice in your account (POST /text-to-voice/create-voice-from-preview).

Get information about the authenticated user (GET /user). Identity + connectivity probe.

Get the authenticated user's subscription details, character quota and usage (GET /user/subscription).

Remove background noise from an audio file, isolating speech (POST /audio-isolation). Multipart upload; the response body is binary audio.

List the available speech models (GET /models).

List voices in the public Voice Library (GET /shared-voices). Offset/page-based results.

Generate a sound effect from a text prompt (POST /sound-generation). The response body is binary audio.

Transform speech in an uploaded audio file into a target voice (POST /speech-to-speech/{voice_id}). Multipart upload; the response body is binary audio.

Transcribe an uploaded audio or video file into text (POST /speech-to-text). Multipart upload; returns a JSON transcript.