nari-labs/dia2
TTS model capable of streaming conversational audio in realtime.
This tool helps create realistic, streaming conversational audio from text, perfect for interactive applications. You provide written dialogue, optionally with existing audio to set the voice, and it generates spoken audio instantly, as if a natural conversation is unfolding. It's ideal for developers building real-time voice assistants, interactive characters, or speech-to-speech systems.
1,100 stars.
Use this if you need to generate human-like spoken dialogue in real time, where audio starts playing as soon as the first few words are available, rather than waiting for the full text.
Not ideal if you require consistent, high-quality audio with a specific, unchanging voice for all generations without prior voice conditioning, or if you need to generate audio longer than two minutes.
Stars
1,100
Forks
91
Language
Python
License
Apache-2.0
Category
Last pushed
Nov 29, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/nari-labs/dia2"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
devnen/Chatterbox-TTS-Server
Self-host the powerful Chatterbox TTS model. This server offers a user-friendly Web UI, flexible...
jamiepine/voicebox
The open-source voice synthesis studio
daswer123/xtts-api-server
A simple FastAPI Server to run XTTSv2
Aivis-Project/AivisSpeech-Engine
AivisSpeech Engine: AI Voice Imitation System - Text to Speech Engine
jianchang512/ChatTTS-ui
一个简单的本地网页界面，使用ChatTTS将文字合成为语音，同时支持对外提供API接口。A simple native web interface that uses ChatTTS to...