GPT-SoVITS
Voice Generator
An AI system for generating human-like voices from text inputs, using deep learning techniques and pre-trained models.
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
37k stars
218 watching
4k forks
Language: Python
last commit: almost 2 years agoLinked from 1 awesome list
text-to-speechttsvitsvoice-clonevoice-cloneaivoice-cloning
hannibal046/awesome-llmRelated projects:
| Repository | Description | Stars |
|---|---|---|
 jasonppy/voicecraft | A neural codec model for speech editing and text-to-speech synthesis in real-time, using few seconds of reference audio. | 7,744 |
 metavoiceio/metavoice-src | A deep learning model for generating human-like speech | 3,936 |
 neonbjb/tortoise-tts | An open-source text-to-speech system trained with high-quality audio capabilities | 13,373 |
 coqui-ai/tts | A deep learning toolkit for generating human-like speech from text | 36,118 |
 plachtaa/vall-e-x | A research implementation of Microsoft's VALL-E X zero-shot TTS model for multilingual text-to-speech synthesis and voice cloning | 7,719 |
| coqui-ai/stt | A toolkit for building and deploying speech-to-text models using deep learning techniques | 2,302 |
 mozilla/tts | An open-source project providing a suite of deep learning models and tools for advanced text-to-speech synthesis. | 9,466 |
 mshumer/gpt-prompt-engineer | A tool for automating the process of generating and ranking effective prompts for AI models like GPT-4, GPT-3.5-Turbo, or Claude 3 Opus. | 9,411 |
 tensorspeech/tensorflowtts | Real-time speech synthesis using state-of-the-art architectures | 3,855 |
 openai/whisper | A general-purpose speech recognition system trained on large-scale weak supervision | 72,752 |
 instruction-tuning-with-gpt-4/gpt-4-llm | This project generates instruction-following data using GPT-4 to fine-tune large language models for real-world tasks. | 4,244 |
 jaywalnut310/vits | Develops an end-to-end text-to-speech system that generates more natural audio than existing models | 6,947 |
 minimaxir/gpt-2-simple | A tool for retraining and fine-tuning the OpenAI GPT-2 text generation model on new datasets. | 3,398 |
 camb-ai/mars5-tts | A deep learning-based speech synthesis model that generates natural-sounding audio with controlled prosody. | 2,551 |
 rhasspy/piper | A fast local neural text-to-speech system optimized for small devices | 7,002 |