VibeTTS

Hi PH community! Built a TTS platform that gives you actual control over how the speech sounds. You can visually edit pitch, energy, and timing at the phoneme level instead of just accepting whatever the AI outputs. Want a word to sound more dramatic? Adjust its pitch curve. Need better pacing? Modify the phoneme durations. Want different emphasis? Change the energy levels. The language coverage is incredible- 7000+ languages - all the major ones, rare dialects, even endangered and ancient scripts. Does your business need to reach someone far across the world, or maybe your clients are still in year 1300 speaking Middle English? That is not a problem with VibeTTS. Features: • 7,000+ language support • Pitch, energy and duration editing • Generate infinite voices from seed • Voice cloning from uploaded audio • Voice editing using 6 parameters • Prosody editing of uploaded audio • (almost) Real-time generation • Professional output quality Back story: I was working on AI dubbing projects and kept running into the same problem - existing TTS platforms don't give me enough control to make the speech sound right. I had just 3 general controls that would apply to the whole speech, so fixing a small detail would often cause more trouble. Then I found the Toucan TTS model and thought that it deserved its own app so here we are. You can try my app out for free at vibetts.com I'd love to hear what you guys think about it. Thanks and have a nice day :)