Wiro - Voxcpm icon

Wiro - Voxcpm

Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning

Wiro - Voxcpm

AI-generated

Overview

This node integrates with the Wiro VoxCPM API to perform tokenizer-free text-to-speech (TTS) synthesis for context-aware speech generation and voice cloning. It accepts an input audio URL and reference audio text (both optional but must be provided together if used), along with a prompt, configuration value, and inference steps to guide the speech synthesis process. The node sends these parameters to the Wiro API, waits for the task to complete by polling the API, and then outputs the status and resulting audio URL. This node is useful for generating realistic speech outputs based on textual prompts and optional audio references, suitable for applications like voice cloning, speech generation, and audio content creation.

Use Case Examples

  1. Generating speech from a text prompt with optional reference audio to clone a voice.
  2. Creating context-aware speech synthesis outputs for multimedia projects.

Properties

Name Meaning
Input Audio URL URL of the input audio to be used as a reference for voice cloning or speech generation. Must be provided together with Reference Audio Text or both left empty.
Reference Audio Text Text corresponding to the reference audio. Must be provided together with Input Audio URL or both left empty.
Prompt Text prompt guiding the speech synthesis process. This is a required input.
Cfg Value Configuration value controlling language model guidance on LocDiT. Higher values improve adherence to the prompt but may reduce quality.
Inference Steps Number of inference timesteps for LocDiT. Higher values improve result quality but increase processing time.

Output

JSON

  • taskid - Identifier of the speech synthesis task assigned by the Wiro API.
  • url - URL of the generated audio output after task completion.
  • status - Status of the task, indicating if it completed successfully or failed.

Dependencies

  • Wiro API with API key and secret credentials

Troubleshooting

  • If the node throws an error about missing task ID or socket access token, it indicates the Wiro API response was invalid or incomplete. Check API credentials and request parameters.
  • Polling may fail or timeout if the task does not complete; ensure network connectivity and valid tokens.
  • Incorrect or missing input audio URL and reference text pairing can cause synthesis failure; both must be provided together or both omitted.

Links

Discussion