ChatTTS and SpeechGPT

One is a foundational speech synthesis model, while the other is a client-side integration of ChatGPT with voice interaction capabilities, making them complements where the latter could potentially utilize the former's speech generation for its output.

ChatTTS
76
Verified
SpeechGPT
47
Emerging
Maintenance 10/25
Adoption 21/25
Maturity 25/25
Community 20/25
Maintenance 2/25
Adoption 13/25
Maturity 18/25
Community 14/25
Stars: 38,924
Forks: 4,223
Downloads: 6,452
Commits (30d): 0
Language: Python
License: AGPL-3.0
Stars: 29
Forks: 5
Downloads: 565
Commits (30d): 0
Language: Python
License: MIT
No risk flags
Stale 6m

About ChatTTS

2noise/ChatTTS

A generative speech model for daily dialogue.

Based on the README, here's the technical summary: Built on a transformer architecture trained on 100,000+ hours of multilingual audio, ChatTTS enables fine-grained prosodic control through special tokens for laughter, pauses, and interjections while supporting multiple speakers via speaker embeddings. The model includes a discrete VAE encoder for zero-shot speaker inference and streaming audio generation capabilities, supporting English and Chinese with plans for additional languages.

About SpeechGPT

Jdka1/SpeechGPT

Free ChatGPT voice interaction and integration into python workflows.

Scores updated daily from GitHub, PyPI, and npm data. How scores work