ElevenLabs Text-to-Speech icon

ElevenLabs Text-to-Speech

Converta texto em fala usando a API da ElevenLabs

ElevenLabs Text-to-Speech

AI-generated

Overview

This node converts text into speech audio using the ElevenLabs Text-to-Speech API. It allows users to input text and select a voice and synthesis model to generate spoken audio output. This is useful for automating voice content creation, such as generating voiceovers for videos, creating audio versions of articles or messages, or building interactive voice applications.

Practical examples include:

  • Creating podcast intros or narrations from written scripts.
  • Generating audio alerts or notifications in custom workflows.
  • Producing multilingual voice content by selecting different voice models.

Properties

Name Meaning
Voz ID of the voice to be used for speech synthesis (e.g., "21m00Tcm4TlvDq8ikWAM").
Texto The text string that will be converted into speech.
Modelo Speech synthesis model to use. Options:
- Eleven Multilingual v2
- Eleven Turbo v2
- Eleven English v1
- Eleven Multilingual v1
- Eleven Monolingual v1
- Eleven Flash v2.5
Nome do Campo Binário Name of the binary field where the generated audio file will be stored in the output data.
Opções Avançadas Advanced options including:
- Estabilidade (stability): Voice consistency between generations (0-1).
- Similaridade (similarity_boost): Closeness to original voice (0-1).
- Estilo (style): Amount of style/expressiveness transferred (0-1).
- Formato de Saída (output_format): Audio file format. Options: MP3, FLAC, WAV, PCM variants, Opus, Ulaw, Mulaw.

Output

The node outputs an array of items, each containing:

  • json field with:

    • success: boolean indicating if synthesis was successful.
    • voiceId: the voice ID used.
    • modelId: the synthesis model used.

  • binary field with:

    • A binary property named as specified by the user (Nome do Campo Binário), containing the generated audio file data.
    • The audio file is encoded in the selected output format (e.g., MP3, FLAC, WAV).

The binary data can be used downstream in workflows for playback, storage, or further processing.

Dependencies

  • Requires an API key credential for the ElevenLabs Text-to-Speech service.
  • Needs network access to call the ElevenLabs API endpoint.
  • No additional external dependencies beyond the ElevenLabs API.

Troubleshooting

  • Common issues:

    • Invalid or missing voice ID or model ID may cause API errors.
    • Incorrect API credentials or expired tokens will result in authentication failures.
    • Unsupported or incorrectly specified output formats might cause unexpected results or errors.
    • Large text inputs could lead to timeouts or rate limiting by the API.

  • Error messages:

    • API error responses are caught and handled; the node returns error details per item.
    • Authentication errors typically indicate invalid API keys—verify and update credentials.
    • Network errors suggest connectivity issues—check internet access and firewall settings.
    • If the binary data is empty or corrupted, verify the output format and voice parameters.

Links and References

Discussion