Using<a target="_blank" rel="ugc" href="https://github.com/niknah/ComfyUI-F5-TTS">https://github.com/niknah/ComfyUI-F5-TTS</a>Text to speech in comfy UIFeatures<ul><li>generates audio from a text prompt</li><li>custom voice from 15 seconds of talking audio.</li></ul>Included simple flow with just TTS saving audioIncluded advanced flow with lipsync video loader and face restore after.Included 2 face video samples to test onIncluded 3 voice samplespokimane - Streamer<a target="_blank" rel="ugc" href="https://www.instagram.com/pokimanelol/?hl=en">https://www.instagram.com/pokimanelol/?hl=en</a>Ruby - ASMR Artist<a target="_blank" rel="ugc" href="https://www.youtube.com/@rubybubyruby">https://www.youtube.com/@rubybubyruby</a>Voice samples must go in the input directory directly. No subfolders.To make your own sample just get a .wav of the voice you want. Cut it to 15-50 secondsPut it in the input directory, then make a empty .txt file with same name as the .wav and it should populate in comfy node when you refresh. Thats it.NotesAudio can be saved as sets voice.wavvoice.txtvoice.emotion.wavvoice.emotion.txtUsing just the voice.wav as sample, These can be called in the prompt with{main} or {emotion} before the text allowing you to change tones.This can be used to store many people in 1 set, allowing talking between people.talkset.jenny.wavtalkset.jenny.txttalkset.molly.wavtalkset.molly.txtCalled with {jenny} or {molly} before the text allowing you to change people.

Files with SHA256: 80f14c4ab1c4e60c7332f09301b00922754a1426c3c54fd1f8f4165ac4593470