ElevenLabs

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.

Usage Instructions

Integrate ElevenLabs into the workflow. Convert text to speech, generate sound effects, transform voices, isolate audio, and manage voices, models, and account settings.

Actions

elevenlabs_tts

Convert text to speech using ElevenLabs voices

Input

ParameterTypeRequiredDescription
textstringYesThe text to convert to speech (e.g., "Hello, welcome to our service!")
voiceIdstringYesThe ID of the voice to use (e.g., "21m00Tcm4TlvDq8ikWAM" for Rachel)
modelIdstringNoThe ID of the model to use (e.g., "eleven_multilingual_v2", "eleven_turbo_v2"). Defaults to eleven_monolingual_v1
stabilitynumberNoVoice 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
similarityBoostnumberNoSimilarity 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
apiKeystringYesYour ElevenLabs API key

Output

ParameterTypeDescription
audioUrlstringThe URL of the generated audio
audioFilefileThe generated audio file

elevenlabs_sound_effects

Generate a sound effect from a text prompt using ElevenLabs

Input

ParameterTypeRequiredDescription
apiKeystringYesYour ElevenLabs API key
textstringYesThe prompt describing the sound effect (e.g., "thunder rumbling in the distance")
modelIdstringNoThe model to use (defaults to eleven_text_to_sound_v2)
durationSecondsnumberNoLength of the sound in seconds (0.5-30). Omit to auto-determine
promptInfluencenumberNoHow closely to follow the prompt from 0.0 to 1.0 (default 0.3)
loopbooleanNoWhether to generate a seamlessly looping sound effect (default false)

Output

ParameterTypeDescription
audioUrlstringURL of the generated sound effect
audioFilefileThe generated sound effect file

elevenlabs_speech_to_speech

Convert audio into a chosen ElevenLabs voice while preserving content and emotion

Input

ParameterTypeRequiredDescription
apiKeystringYesYour ElevenLabs API key
voiceIdstringYesThe ID of the target voice to convert the audio into
audioFilefileYesThe source audio file to convert (e.g., MP3, WAV, M4A)
modelIdstringNoThe model to use (defaults to eleven_english_sts_v2)
removeBackgroundNoisebooleanNoWhether to isolate the voice and remove background noise (default false)

Output

ParameterTypeDescription
audioUrlstringURL of the converted audio
audioFilefileThe converted audio file

elevenlabs_audio_isolation

Remove background noise from an audio file, isolating the speech using ElevenLabs

Input

ParameterTypeRequiredDescription
apiKeystringYesYour ElevenLabs API key
audioFilefileYesThe audio file to isolate speech from (e.g., MP3, WAV, M4A)

Output

ParameterTypeDescription
audioUrlstringURL of the isolated audio
audioFilefileThe isolated audio file

elevenlabs_list_voices

List the voices available in your ElevenLabs account

Input

ParameterTypeRequiredDescription
apiKeystringYesYour ElevenLabs API key
searchstringNoSearch term to filter voices by name, description, labels, or category
categorystringNoFilter by category: premade, cloned, generated, or professional
pageSizenumberNoNumber of voices to return (1-100, default 10)
nextPageTokenstringNoPage token from a previous response to fetch the next page of voices

Output

ParameterTypeDescription
voicesarrayList of voices
voiceIdstringUnique voice identifier
namestringVoice name
categorystringVoice category
descriptionstringVoice description
labelsjsonVoice labels (accent, gender, age, use case)
previewUrlstringURL to a preview audio sample
settingsjsonDefault voice settings
totalCountnumberTotal number of matching voices
hasMorebooleanWhether more voices are available
nextPageTokenstringToken to fetch the next page

elevenlabs_get_voice

Get metadata and settings for a specific ElevenLabs voice

Input

ParameterTypeRequiredDescription
apiKeystringYesYour ElevenLabs API key
voiceIdstringYesThe ID of the voice to retrieve (e.g., "21m00Tcm4TlvDq8ikWAM")

Output

ParameterTypeDescription
voiceIdstringUnique voice identifier
namestringVoice name
categorystringVoice category
descriptionstringVoice description
labelsjsonVoice labels (accent, gender, age, use case)
previewUrlstringURL to a preview audio sample
settingsjsonDefault voice settings
availableForTiersarraySubscription tiers the voice is available on
highQualityBaseModelIdsarrayModel IDs that support high-quality output for this voice
isOwnerbooleanWhether the current user owns this voice

elevenlabs_get_voice_settings

Get the configured settings for a specific ElevenLabs voice

Input

ParameterTypeRequiredDescription
apiKeystringYesYour ElevenLabs API key
voiceIdstringYesThe ID of the voice whose settings to retrieve

Output

ParameterTypeDescription
stabilitynumberVoice stability (0.0-1.0)
similarityBoostnumberSimilarity boost (0.0-1.0)
stylenumberStyle exaggeration (0.0-1.0)
useSpeakerBoostbooleanWhether speaker boost is enabled
speednumberSpeech speed (1.0 = normal)

elevenlabs_edit_voice_settings

Update the settings for a specific ElevenLabs voice

Input

ParameterTypeRequiredDescription
apiKeystringYesYour ElevenLabs API key
voiceIdstringYesThe ID of the voice to update
stabilitynumberNoVoice stability from 0.0 to 1.0 (default 0.5)
similarityBoostnumberNoSimilarity boost from 0.0 to 1.0 (default 0.75)
stylenumberNoStyle exaggeration from 0.0 to 1.0 (default 0)
useSpeakerBoostbooleanNoWhether to enhance similarity to the original speaker (default true)
speednumberNoSpeech speed where 1.0 is normal (default 1.0)

Output

ParameterTypeDescription
statusstringRequest outcome ("ok" on success)

elevenlabs_list_models

List the models available in ElevenLabs

Input

ParameterTypeRequiredDescription
apiKeystringYesYour ElevenLabs API key

Output

ParameterTypeDescription
modelsarrayList of available models
modelIdstringUnique model identifier
namestringModel name
descriptionstringModel description
canDoTextToSpeechbooleanSupports text-to-speech
canDoVoiceConversionbooleanSupports voice conversion
canUseStylebooleanSupports the style parameter
canUseSpeakerBoostbooleanSupports speaker boost
languagesarrayLanguages supported by the model
languageIdstringLanguage code
namestringLanguage name

elevenlabs_get_user

Get account and subscription information for the ElevenLabs user

Input

ParameterTypeRequiredDescription
apiKeystringYesYour ElevenLabs API key

Output

ParameterTypeDescription
userIdstringUnique user identifier
isNewUserbooleanWhether the user is new
subscriptionobjectSubscription and usage details
tierstringSubscription tier
characterCountnumberCharacters used this period
characterLimitnumberCharacter quota for this period
canExtendCharacterLimitbooleanWhether the character limit can be extended
statusstringSubscription status
nextCharacterCountResetUnixnumberUnix timestamp when the character count resets

On this page