elevenlabs

Converts text into speech using a voice of your choice and returns audio.

11 APIs 16 Features

APIs

ElevenLabs Text to Speech API

The ElevenLabs Text to Speech API converts text into lifelike spoken audio with nuanced intonation, pacing, and emotional awareness. It supports multiple output formats includin...

ElevenLabs Speech to Text API

The ElevenLabs Speech to Text API provides state-of-the-art transcription capabilities, converting spoken audio into accurate text. It supports multiple audio formats and langua...

ElevenLabs Voice Cloning API

The ElevenLabs Voice Cloning API allows developers to create custom AI voices from audio recordings. Instant Voice Cloning requires as little as 60 seconds of clean audio to gen...

ElevenLabs Voices API

The ElevenLabs Voices API provides management capabilities for the voice library, including listing, retrieving, creating, editing, and deleting voices. Developers can access a ...

ElevenLabs Sound Effects API

The ElevenLabs Sound Effects API generates cinematic sound effects from text descriptions. Developers can describe the desired sound in natural language and receive high-quality...

ElevenLabs Audio Isolation API

The ElevenLabs Audio Isolation API removes background noise from audio recordings, isolating vocal tracks from ambient sounds and interference. This is useful for cleaning up re...

ElevenLabs Dubbing API

The ElevenLabs Dubbing API enables automatic translation and voice-over of audio and video content into different languages. It preserves the original speaker's voice characteri...

ElevenLabs Voice Changer API

The ElevenLabs Voice Changer API performs speech-to-speech conversion, replacing one voice with another while preserving the original speech content, timing, and emotional deliv...

ElevenLabs Music Generation API

The ElevenLabs Music Generation API creates music from text prompts, allowing developers to generate original musical compositions programmatically. Users describe the desired g...

ElevenLabs Conversational AI API

The ElevenLabs Conversational AI API enables developers to build interactive voice agents that can engage in natural, real-time conversations. It combines speech recognition, la...

ElevenLabs Studio API

The ElevenLabs Studio API provides programmatic access to the ElevenLabs Studio project management system. Developers can create, manage, and render long-form audio content proj...

Collections

GraphQL

ElevenLabs GraphQL Schema

title: ElevenLabs GraphQL Schema

GRAPHQL

Pricing Plans

Elevenlabs Plans Pricing

7 plans

PLANS

Rate Limits

Elevenlabs Rate Limits

7 limits

RATE LIMITS

FinOps

Features

Free: 10k credits/mo with TTS/STT/Sound effects
Starter at $6/mo: 30k credits, commercial license, IVC
Creator at $11/mo: 121k credits, Professional Voice Cloning
Pro at $99/mo: 600k credits, 44.1kHz PCM
Scale at $299/mo: 1.8M credits, team collaboration
Business at $990/mo: 6M credits, low-latency TTS at 5c/min
Enterprise custom: HIPAA BAA, SSO, custom concurrency
Concurrent: 2 Free, 3 Starter, 5 Creator, 10 Pro, 15 Scale/Business
TTS API with multilingual voices
STT (Scribe) API
Dubbing API for video translation
Voice cloning (Instant + Professional)
Sound Effects generation
Music generation
Conversational AI (voice agents)
WebSocket streaming for low-latency synthesis

Event Specifications

ElevenLabs Conversational AI Events

The ElevenLabs Conversational AI WebSocket API enables real-time, interactive voice conversations with AI agents. It supports bidirectional audio streaming, text events, and con...

ASYNCAPI

ElevenLabs Text to Speech Streaming Events

The ElevenLabs Text to Speech WebSocket API enables bidirectional streaming for text-to-speech conversion. Clients send text chunks incrementally and receive audio chunks as the...

ASYNCAPI

ElevenLabs Webhook Events

The ElevenLabs Webhook system delivers event notifications to configured endpoints when specific actions occur within the platform. This includes post-call webhooks from Convers...

ASYNCAPI

Semantic Vocabularies

Elevenlabs Context

0 classes · 11 properties

JSON-LD

JSON Structure

Elevenlabs Structure

0 properties

JSON STRUCTURE

Resources

👥
GitHubOrganization
GitHubOrganization
🔗
LinkedIn
LinkedIn
🔗
JSONLD
JSONLD
🔗
JSONSchema
JSONSchema
🔗
JSONSchema
JSONSchema
🔗
JSONSchema
JSONSchema
🔗
LlmsText
LlmsText

Sources

Raw ↑
opencollection: 1.0.0
info:
  name: ElevenLabs Voices API
  version: '1.0'
request:
  auth:
    type: apikey
    key: xi-api-key
    value: '{{xi-api-key}}'
    placement: header
items:
- info:
    name: Voices
    type: folder
  items:
  - info:
      name: List voices
      type: http
    http:
      method: GET
      url: https://api.elevenlabs.io/v1/voices
      params:
      - name: show_legacy
        value: ''
        type: query
        description: Whether to include legacy voices in the response.
    docs: Returns a list of all available voices, including pre-built and custom voices. Each voice includes metadata such
      as name, labels, description, and available settings.
  - info:
      name: Get voice
      type: http
    http:
      method: GET
      url: https://api.elevenlabs.io/v1/voices/:voice_id
      params:
      - name: voice_id
        value: ''
        type: path
        description: The identifier of the voice.
      - name: with_settings
        value: ''
        type: query
        description: Whether to include the voice settings in the response.
    docs: Returns metadata about a specific voice including its settings, samples, labels, and description.
  - info:
      name: Delete voice
      type: http
    http:
      method: DELETE
      url: https://api.elevenlabs.io/v1/voices/:voice_id
      params:
      - name: voice_id
        value: ''
        type: path
        description: The identifier of the voice.
    docs: Deletes a voice from the user's voice library. This action is irreversible and removes all associated samples and
      settings.
  - info:
      name: Edit voice
      type: http
    http:
      method: POST
      url: https://api.elevenlabs.io/v1/voices/:voice_id/edit
      params:
      - name: voice_id
        value: ''
        type: path
        description: The identifier of the voice.
      body:
        type: multipart-form
        data: []
    docs: Updates the metadata and settings for an existing voice. Allows changing the name, description, labels, and uploading
      new samples.
  - info:
      name: Add voice
      type: http
    http:
      method: POST
      url: https://api.elevenlabs.io/v1/voices/add
      body:
        type: multipart-form
        data: []
    docs: Creates a new voice from uploaded audio samples. The voice can then be used with text-to-speech and other audio
      generation endpoints.
- info:
    name: Voice Settings
    type: folder
  items:
  - info:
      name: Get voice settings
      type: http
    http:
      method: GET
      url: https://api.elevenlabs.io/v1/voices/:voice_id/settings
      params:
      - name: voice_id
        value: ''
        type: path
        description: The identifier of the voice.
    docs: Returns the settings for a specific voice including stability, similarity boost, and style parameters.
  - info:
      name: Edit voice settings
      type: http
    http:
      method: POST
      url: https://api.elevenlabs.io/v1/voices/:voice_id/settings/edit
      params:
      - name: voice_id
        value: ''
        type: path
        description: The identifier of the voice.
      body:
        type: json
        data: '{}'
    docs: Updates the default settings for a specific voice. These settings are used when no per-request overrides are provided.
  - info:
      name: Get default voice settings
      type: http
    http:
      method: GET
      url: https://api.elevenlabs.io/v1/voices/settings/default
    docs: Returns the default voice settings that are applied when no voice-specific or per-request settings are provided.
- info:
    name: Voice Library
    type: folder
  items:
  - info:
      name: List shared voices
      type: http
    http:
      method: GET
      url: https://api.elevenlabs.io/v1/voice-library
      params:
      - name: page_size
        value: ''
        type: query
        description: Number of voices to return per page.
      - name: gender
        value: ''
        type: query
        description: Filter voices by gender.
      - name: language
        value: ''
        type: query
        description: Filter voices by language.
      - name: search
        value: ''
        type: query
        description: Search term to filter voices by name or description.
    docs: Returns a paginated list of voices from the public voice library that can be added to the user's voice collection.
  - info:
      name: Add shared voice
      type: http
    http:
      method: POST
      url: https://api.elevenlabs.io/v1/voice-library/:public_user_id/:voice_id/add
      params:
      - name: public_user_id
        value: ''
        type: path
        description: The public user ID of the voice owner.
      - name: voice_id
        value: ''
        type: path
        description: The identifier of the voice.
      body:
        type: json
        data: '{}'
    docs: Adds a voice from the public library to the user's personal voice collection. The voice can then be used with speech
      generation endpoints.
bundled: true