Overview
This node, named "Botnoi TTS," converts input text into audio using the Botnoi AI Text-to-Speech (TTS) API. It is designed to generate spoken audio files from textual content, supporting multiple languages and a wide variety of speaker voices. This node is useful in scenarios such as creating voiceovers for videos, generating audio notifications, accessibility features, or any automation workflow requiring speech synthesis.
Practical examples:
- Converting customer support messages into audio alerts.
- Generating podcast intros or announcements automatically.
- Creating language learning tools with native speaker voices.
- Producing audio versions of articles or blog posts.
Properties
| Name | Meaning |
|---|---|
| Text | The text string that will be converted into audio. |
| Speaker | The voice used for audio generation. Many speaker options are available, each representing a unique voice identity. |
| Volume | The loudness level of the generated audio, ranging from 0 (mute) to 2 (double volume). |
| Speed | The playback speed of the audio, from 0.5 (half speed) to 2 (double speed). |
| Media Type | The output audio file format; options are MP3 or WAV. |
| Save File | Boolean flag indicating whether to save the generated audio file. |
| Language | The language code of the input text, affecting pronunciation and voice characteristics. Supported languages include Thai, Chinese, Japanese, Burmese, Lao, Vietnamese, Indonesian, Cambodian, Filipino, Arabic, German, Spanish, French, Malay, Portuguese (Brazil), Russian, English, Dutch, Korean, Hindi, Singaporean, Turkish, and Italian. |
Output
The node outputs JSON data containing the response from the Botnoi AI API under the response field. This response typically includes information about the generated audio, such as URLs or metadata related to the audio file.
If the "Save File" option is enabled, the node saves the generated audio file accordingly. The output does not explicitly contain binary data but references the generated audio via the API response.
Dependencies
- Requires an API key credential for the Botnoi AI service to authenticate requests.
- Makes HTTP POST requests to the Botnoi AI TTS endpoint:
https://api-voice.botnoi.ai/openapi/v1/generate_audio. - The node expects proper configuration of the API key credential within n8n.
Troubleshooting
Common issues:
- Invalid or missing API key credential will cause authentication failures.
- Network connectivity problems may prevent successful API calls.
- Providing unsupported language codes or speaker IDs might result in API errors.
- Exceeding rate limits or quota on the Botnoi AI service could lead to request rejections.
Error messages:
- Errors thrown by the node typically originate from failed HTTP requests to the API.
- The node wraps these errors and surfaces them as operation errors with details from the API response.
Resolutions:
- Verify that the API key credential is correctly set up and valid.
- Check network access and firewall settings.
- Confirm that input parameters like language, speaker, and media type are valid.
- Review Botnoi AI service usage limits and ensure compliance.
Links and References
- Botnoi AI Official Website
- Botnoi AI Text-to-Speech API Documentation (hypothetical link, replace with actual if available)