Chatterbox TTS
🍿
Expressive Zeroshot TTS
TEXT TO SPEECH MODELS AND PODCAST GENERATION
Expressive Zeroshot TTS
Note Chatterbox TTS Demo that generates high-quality speech from text with reference audio. Text to synthesize is limited (max chars 300) but batch inference via API Script helps (chunks text and process in sequence). Reference Audio File affects the style of output and Exaggeration level also change the result. Exaggeration controls voice characteristic emphasis cfg_pace is Classifier-free guidance weight Temperature affects speed.
Note Text-to-Speech with Suno/Bark-Small. Slow.
Note MMS Text-to-Speech (English) A Gradio app to run the facebook/mms-tts-eng model for text-to-speech conversion. Fast but single voice used.