ElevenLabs é uma plataforma de text-to-speech de ponta que cria vozes de IA incrivelmente naturais e expressivas. Oferece algumas das vozes sintéticas mais realistas e emocionalmente nuançadas disponíveis hoje, tornando-a ideal para criar conteúdo de áudio realista.
Com o ElevenLabs, você pode:
- Gerar fala com som natural: Crie áudio quase indistinguível da fala humana
- Escolher entre diversas opções de voz: Acesse uma biblioteca de vozes pré-prontas com diferentes sotaques, tons e características
- Clonar vozes: Crie vozes personalizadas com base em amostras de áudio (com as permissões adequadas)
- Controlar parâmetros de fala: Ajuste estabilidade, clareza e tom emocional para refinar a saída
- Adicionar emoções realistas: Incorpore emoções com som natural como felicidade, tristeza ou entusiasmo
No Zoen, a integração do ElevenLabs permite que seus agentes convertam texto em fala realista, aumentando a interatividade e o engajamento das suas aplicações. Isso é particularmente valioso para criar assistentes de voz, gerar conteúdo de áudio, desenvolver aplicações acessíveis ou construir interfaces conversacionais que parecem mais humanas. A integração permite incorporar de forma transparente as capacidades avançadas de síntese de fala do ElevenLabs nos fluxos de trabalho dos seus agentes, preenchendo a lacuna entre a IA baseada em texto e a comunicação humana natural.
Integrate ElevenLabs into the workflow. Convert text to speech, generate sound effects, transform voices, isolate audio, and manage voices, models, and account settings.
Convert text to speech using ElevenLabs voices
| Parameter | Type | Required | Description |
|---|
text | string | Yes | The text to convert to speech (e.g., "Hello, welcome to our service!") |
voiceId | string | Yes | The ID of the voice to use (e.g., "21m00Tcm4TlvDq8ikWAM" for Rachel) |
modelId | string | No | The ID of the model to use (e.g., "eleven_multilingual_v2", "eleven_turbo_v2"). Defaults to eleven_monolingual_v1 |
stability | number | No | Voice stability setting from 0.0 to 1.0 (e.g., 0.5 for balanced, 0.75 for more stable). Higher values produce more consistent output |
similarityBoost | number | No | Similarity boost setting from 0.0 to 1.0 (e.g., 0.75 for natural, 1.0 for maximum similarity). Higher values make the voice more similar to the original |
apiKey | string | Yes | Your ElevenLabs API key |
| Parameter | Type | Description |
|---|
audioUrl | string | The URL of the generated audio |
audioFile | file | The generated audio file |
Generate a sound effect from a text prompt using ElevenLabs
| Parameter | Type | Required | Description |
|---|
apiKey | string | Yes | Your ElevenLabs API key |
text | string | Yes | The prompt describing the sound effect (e.g., "thunder rumbling in the distance") |
modelId | string | No | The model to use (defaults to eleven_text_to_sound_v2) |
durationSeconds | number | No | Length of the sound in seconds (0.5-30). Omit to auto-determine |
promptInfluence | number | No | How closely to follow the prompt from 0.0 to 1.0 (default 0.3) |
loop | boolean | No | Whether to generate a seamlessly looping sound effect (default false) |
| Parameter | Type | Description |
|---|
audioUrl | string | URL of the generated sound effect |
audioFile | file | The generated sound effect file |
Convert audio into a chosen ElevenLabs voice while preserving content and emotion
| Parameter | Type | Required | Description |
|---|
apiKey | string | Yes | Your ElevenLabs API key |
voiceId | string | Yes | The ID of the target voice to convert the audio into |
audioFile | file | Yes | The source audio file to convert (e.g., MP3, WAV, M4A) |
modelId | string | No | The model to use (defaults to eleven_english_sts_v2) |
removeBackgroundNoise | boolean | No | Whether to isolate the voice and remove background noise (default false) |
| Parameter | Type | Description |
|---|
audioUrl | string | URL of the converted audio |
audioFile | file | The converted audio file |
Remove background noise from an audio file, isolating the speech using ElevenLabs
| Parameter | Type | Required | Description |
|---|
apiKey | string | Yes | Your ElevenLabs API key |
audioFile | file | Yes | The audio file to isolate speech from (e.g., MP3, WAV, M4A) |
| Parameter | Type | Description |
|---|
audioUrl | string | URL of the isolated audio |
audioFile | file | The isolated audio file |
List the voices available in your ElevenLabs account
| Parameter | Type | Required | Description |
|---|
apiKey | string | Yes | Your ElevenLabs API key |
search | string | No | Search term to filter voices by name, description, labels, or category |
category | string | No | Filter by category: premade, cloned, generated, or professional |
pageSize | number | No | Number of voices to return (1-100, default 10) |
nextPageToken | string | No | Page token from a previous response to fetch the next page of voices |
| Parameter | Type | Description |
|---|
voices | array | List of voices |
↳ voiceId | string | Unique voice identifier |
↳ name | string | Voice name |
↳ category | string | Voice category |
↳ description | string | Voice description |
↳ labels | json | Voice labels (accent, gender, age, use case) |
↳ previewUrl | string | URL to a preview audio sample |
↳ settings | json | Default voice settings |
totalCount | number | Total number of matching voices |
hasMore | boolean | Whether more voices are available |
nextPageToken | string | Token to fetch the next page |
Get metadata and settings for a specific ElevenLabs voice
| Parameter | Type | Required | Description |
|---|
apiKey | string | Yes | Your ElevenLabs API key |
voiceId | string | Yes | The ID of the voice to retrieve (e.g., "21m00Tcm4TlvDq8ikWAM") |
| Parameter | Type | Description |
|---|
voiceId | string | Unique voice identifier |
name | string | Voice name |
category | string | Voice category |
description | string | Voice description |
labels | json | Voice labels (accent, gender, age, use case) |
previewUrl | string | URL to a preview audio sample |
settings | json | Default voice settings |
availableForTiers | array | Subscription tiers the voice is available on |
highQualityBaseModelIds | array | Model IDs that support high-quality output for this voice |
isOwner | boolean | Whether the current user owns this voice |
Get the configured settings for a specific ElevenLabs voice
| Parameter | Type | Required | Description |
|---|
apiKey | string | Yes | Your ElevenLabs API key |
voiceId | string | Yes | The ID of the voice whose settings to retrieve |
| Parameter | Type | Description |
|---|
stability | number | Voice stability (0.0-1.0) |
similarityBoost | number | Similarity boost (0.0-1.0) |
style | number | Style exaggeration (0.0-1.0) |
useSpeakerBoost | boolean | Whether speaker boost is enabled |
speed | number | Speech speed (1.0 = normal) |
Update the settings for a specific ElevenLabs voice
| Parameter | Type | Required | Description |
|---|
apiKey | string | Yes | Your ElevenLabs API key |
voiceId | string | Yes | The ID of the voice to update |
stability | number | No | Voice stability from 0.0 to 1.0 (default 0.5) |
similarityBoost | number | No | Similarity boost from 0.0 to 1.0 (default 0.75) |
style | number | No | Style exaggeration from 0.0 to 1.0 (default 0) |
useSpeakerBoost | boolean | No | Whether to enhance similarity to the original speaker (default true) |
speed | number | No | Speech speed where 1.0 is normal (default 1.0) |
| Parameter | Type | Description |
|---|
status | string | Request outcome ("ok" on success) |
List the models available in ElevenLabs
| Parameter | Type | Required | Description |
|---|
apiKey | string | Yes | Your ElevenLabs API key |
| Parameter | Type | Description |
|---|
models | array | List of available models |
↳ modelId | string | Unique model identifier |
↳ name | string | Model name |
↳ description | string | Model description |
↳ canDoTextToSpeech | boolean | Supports text-to-speech |
↳ canDoVoiceConversion | boolean | Supports voice conversion |
↳ canUseStyle | boolean | Supports the style parameter |
↳ canUseSpeakerBoost | boolean | Supports speaker boost |
↳ languages | array | Languages supported by the model |
↳ languageId | string | Language code |
↳ name | string | Language name |
Get account and subscription information for the ElevenLabs user
| Parameter | Type | Required | Description |
|---|
apiKey | string | Yes | Your ElevenLabs API key |
| Parameter | Type | Description |
|---|
userId | string | Unique user identifier |
isNewUser | boolean | Whether the user is new |
subscription | object | Subscription and usage details |
↳ tier | string | Subscription tier |
↳ characterCount | number | Characters used this period |
↳ characterLimit | number | Character quota for this period |
↳ canExtendCharacterLimit | boolean | Whether the character limit can be extended |
↳ status | string | Subscription status |
↳ nextCharacterCountResetUnix | number | Unix timestamp when the character count resets |