dia
by nari-labs · GitHub
A TTS model capable of generating ultra-realistic dialogue in one pass.
⭐ Stars
19.3k
🍴 Forks
1.7k
📜 License
Apache-2.0
Commercial use OK📅 Created
2025
🔄 Last commit
8 mo ago
🏷️ Category
ai
💻 Language
You maintain this project?
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
📈 Star history
2026-06-282026-07-22
📄 About
A TTS model capable of generating ultra-realistic dialogue in one pass.
❓ Frequently asked questions
What is dia?
A TTS model capable of generating ultra-realistic dialogue in one pass.
Is dia open source?
dia is an open-source project. It is released under the Apache-2.0 license.
Is dia free?
Yes. dia is free and open source — you can use, modify and self-host it.
🏅 Maintainer of this project?
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://opensourceai.tech/project/nari-labs-dia.html)
🧬 Shares DNA with🧬 View the DNA map →
dia2
TTS model capable of streaming conversational audio in realtime.
★ 1.2k · open-weight
sharesopen-weighttext-to-speech
voicebox-pytorch
Implementation of Voicebox, new SOTA Text-to-speech network from MetaAI, in Pytorch
★ 698 · artificial-intelligence
sharestext-to-speech
e2-tts-pytorch
Implementation of E2-TTS, "Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS", in Pyto…
★ 516 · artificial-intelligence
sharestext-to-speech
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.