TTS-Audio-Suite
A local text-to-speech extension for ComfyUI that combines voice cloning, voice conversion, character dialogue and subtitle-timed audio.
Alternative to:
TTS-Audio-Suite is a ComfyUI extension for creators producing narration, character dialogue and speech matched to subtitles on their own hardware. It brings several speech engines and audio editing tools into the same workspace.
- Speech and voice design: Generate speech with engines including F5-TTS, Chatterbox, VibeVoice and Qwen3-TTS, with voice cloning and reusable voice design available through compatible engines.
- Subtitle timing: Generate audio against SRT timings, receive subtitles adjusted to the resulting speech, and regenerate only edited segments; transcription and text-to-SRT tools also help prepare subtitles.
- Character dialogue: Switch voices and languages within a script, use VibeVoice for long-form multi-speaker narration, or add emotion and delivery tags with Higgs Audio v3.
- Speech editing and conversion: Edit targeted speech with F5-TTS, change emotion or speaking style with Step Audio EditX, and convert voices or train voice models through RVC.
- Audio cleanup and effects: Remove vocals or noise, inspect waveforms, apply post-processing and generate sound effects alongside speech.
The extension runs locally within ComfyUI and builds on the original ChatterBox Voice project. Language coverage, voice controls and hardware demands depend on the selected engine. Automatic text chunking supports long scripts, while compatible Qwen3-TTS, MOSS and OmniVoice engines can create reusable voices.
