Back to AI Repos
Audio

nari-labs/dia

A TTS model capable of generating ultra-realistic dialogue in one pass.

nari-labs/dia is an open-source project in the audio space, written mainly in Python.

It sits at around 19.4k stars and 1.7k forks, and was last pushed on 2025-11-19.

Everything on this page — the summary, the category and the how-to — is written by HowToPrompts; the link below goes to the original project.

CategoryAudio
Stars19.4k
Forks1.7k
LanguagePython
Last pushed2025-11-19
Topicsai, open-weight, text-to-speech
git clone https://github.com/nari-labs/dia.git

How to use it

  1. Clone the repository with the command above.
  2. Follow its own README for dependencies and setup.
  3. Check the open issues and last-push date before you build on it.
Compiled and written by HowToPrompts from public sources. Open on GitHub ↗

Related in Audio

RVC-Boss/GPT-SoVITS1 min voice data can also be used to train a good TTS model! (few shot voice cloning)CorentinJ/Real-Time-Voice-CloningClone a voice in 5 seconds to generate arbitrary speech in real-timeggml-org/whisper.cppPort of OpenAI's Whisper model in C/C++coqui-ai/TTSA deep learning toolkit for Text-to-Speech, battle-tested in research and productionmyshell-ai/OpenVoiceInstant voice cloning by MIT and MyShell. Audio foundation model.babysor/MockingBirdClone a voice in 5 seconds to generate arbitrary speech in real-timeOpenBMB/VoxCPMVoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Clonincjpais/HandyA free, open source, and extensible speech-to-text application that works completely offline.Zackriya-Solutions/meetilyPrivacy first, AI meeting assistant with 4x faster Parakeet/Whisper live transcription, speaker diarization, adeezer/spleeterDeezer source separation library including pretrained models.
← Back to AI Repos