VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
- tts
- voice-cloning
- voice-generation
- voice-ai
Repository Index
84,085 visible repositories in the index
1–6 of 6 · Most stars
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
- audio-generation
- gpt-4o
- text-to-speech
- tts
A TensorFlow Implementation of Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model
- tts
- tensorflow
- speech-synthesis-model
- speech
Talking Head (3D): A JavaScript class for real-time lip-sync using full-body 3D avatars.
- 3d-avatar
- lip-sync
- text-to-speech
- talking-head
Sophon-Realtime v1.1: open full-duplex voice models that hear your tone and speak with one. Zero-shot voice cloning, one GPU with vLLM-Omni, OpenAI Realtime / GPT-Live compatible. Apache-2.0.
- full-duplex
- open-source
- paralinguistics
- realtime
Capacitor plugin to synthesize speech from text with full control over language, voice, pitch, rate, and volume.