Overview
This node integrates with the Mobvoi API to perform text-to-speech (TTS) conversion. It allows users to input text and convert it into spoken audio using various configurable parameters such as speaker voice, audio format, speed, pitch, and volume. This is useful for automating voice generation in applications like virtual assistants, accessibility tools, or content narration.
Typical use cases include:
- Generating audio versions of written content.
- Creating voice prompts or announcements.
- Producing customized speech outputs with different voices and audio settings.
Properties
| Name | Meaning |
|---|---|
| Text | The text string that will be converted into speech. |
| Speaker | The voice or speaker profile used for speech synthesis. Default is "xiaoyi_meet". |
| Audio_type | The output audio file format. Commonly "mp3". |
| Speed | The speaking speed multiplier (e.g., "1.0" for normal speed). |
| Rate | The audio sample rate in Hz (e.g., "24000"). |
| Volume | The volume level of the output audio (default "1"). |
| Pitch | The pitch adjustment for the speech output (default "0.0"). |
| Streaming | Boolean flag indicating whether to stream the audio output or not (default false). |
Note: Some properties share the same internal name ("rate") in the source but represent different concepts (Rate, Volume, Pitch, Streaming). This appears to be a code issue but from usage perspective they correspond to distinct parameters.
Output
The node outputs JSON data containing the result of the text-to-speech operation. Typically, this includes:
- A field with the synthesized audio data encoded in the specified audio format (e.g., mp3).
- Metadata about the audio such as duration, sample rate, or encoding details may also be included depending on the API response.
If streaming is enabled, the node may output audio data progressively.
Binary data output (audio files) is expected to be handled by the node, allowing downstream nodes to process or save the audio.
Dependencies
- Requires an API key credential for authenticating with the Mobvoi API.
- Network access to Mobvoi's TTS endpoints (
https://open.mobvoi.comand related hosts). - Proper configuration of the API key credential within n8n.
Troubleshooting
- Authentication errors: Ensure the API key credential is correctly configured and has necessary permissions.
- Invalid parameter values: Check that text is non-empty and audio parameters (speed, rate, volume, pitch) are within acceptable ranges.
- Network issues: Verify connectivity to Mobvoi API endpoints.
- Unexpected output format: Confirm the requested audio type is supported by the API.
- Streaming failures: If streaming is enabled but fails, try disabling streaming or check network stability.
Links and References
- Mobvoi Official Website
- Mobvoi API Documentation (for detailed API usage and parameters)