MeanVC2 Voice Conversion

Tools

• meanvc2_voice_conversion_convert Convert the voice in `source_audio` to the speaker heard in `reference_audio`. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool. Returns: (sample_rate, waveform) tuple with the converted 16 kHz audio.
• meanvc2_voice_conversion_prep_live_reference Prepare a live session from an uploaded/recorded target-voice reference. Called from a regular ``gr.Audio`` component in the Live tab (upload or mic-record — NOT streaming). It extracts the 256-d speaker embedding once from the provided reference file and stashes it in a fresh live session, returning that session id so the custom mic-streaming HTML component can use it for the live conversion loop. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool. Returns: A session id string (empty if no reference was provided).
• meanvc2_voice_conversion_run_live_session One long-lived GPU session that streams live voice conversion. This is the SDXL-Turbo continuous-generator loop adapted to audio. It holds a *single* ZeroGPU allocation for the whole session (instead of forking a fresh worker per mic slice) and, for the full session window, drains the per-session input queue that ``live_push`` fills with raw mic audio, accumulates it in a buffer, converts it once enough has piled up, and writes the converted audio to the per-session output queue for ``live_pull`` to hand back to the browser. Nothing that arrives is dropped: short slices are buffered until a full MeanVC2 slice can be produced, and any tail shorter than one slice is kept for the next iteration.

No tool matches.

As the server's own listing gives them. We never call a tool.