FireRedAudio

Tools

• fireredaudio_tts_demo__on_task_change
• fireredaudio_tts_demo_clone_voice Clone a voice from a short reference clip and read new text in it (zero-shot TTS). 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: Path to the generated 24 kHz wav, and the seed that produced it.
• fireredaudio_tts_demo_design_voice Synthesise speech from a natural-language description of the voice (Instruct TTS). Returns: Path to the generated 24 kHz wav, the timbre tags the model chose, and the seed.
• fireredaudio_tts_demo_edit_speech Edit an existing recording from a text instruction, keeping the original voice. 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: Path to the edited 24 kHz wav, the rewritten transcript (semantic edits), and the seed.
• fireredaudio_tts_demo_understand_audio Transcribe an audio clip, or answer a free-form question about it. 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: The answer, and the chain-of-thought reasoning (empty when thinking is off).

No tool matches.

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