Subject
3 entries
Tts
Bookmarks
Qwen3-TTS-12Hz-1.7B-CustomVoice: open custom voice TTS
Qwen3-TTS-12Hz-1.7B-CustomVoice is Alibaba's compact open TTS model with custom voice cloning capability — 1.7B parameters, 12Hz token rate, available on Hugging Face. Part of the Qwen3 model family.
WhisperFusion: real-time voice conversations with AI
WhisperFusion is Collabora's pipeline for real-time voice conversations with AI — combining WhisperLive (real-time STT) with WhisperSpeech (TTS) and an LLM to create a fully local end-to-end spoken AI assistant.
TorToiSe TTS: Architectural Design Document
The architectural design document for TorToiSe TTS — James Betker's highly capable open-source voice cloning and text-to-speech system. Explains the multi-model pipeline combining autoregressive and diffusion components that made it state-of-the-art in 2022.