SWSweetSoftPillow·Nov 24, 2025Submission
Open (Apache 2.0) TTS model for streaming conversational audio in realtime
79 points · Open discussionnari-labs
dia2
Python2025–2025
nari-labs / dia2
dia2
TTS model capable of streaming conversational audio in realtime.
2Distinct people
2Mentions
0Explicit recommenders
1.2KGitHub stars
What to know before exploring
What it is
TTS model capable of streaming conversational audio in realtime.
GitHub
Where it is used
No documented product use has been verified yet.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 5:04:57 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by 6-hour interval2 dated mentions
Observed mentions: 2025-11-19 18:59:54 UTC to 2025-11-24 12:28:44 UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| Nov 19, 18:00 | 2025-11-19 18:00:00 UTC | 2025-11-20 00:00:00 UTC | 1 | 1 | 0 |
| Nov 20, 00:00 | 2025-11-20 00:00:00 UTC | 2025-11-20 06:00:00 UTC | 0 | 0 | 0 |
| Nov 20, 06:00 | 2025-11-20 06:00:00 UTC | 2025-11-20 12:00:00 UTC | 0 | 0 | 0 |
| Nov 20, 12:00 | 2025-11-20 12:00:00 UTC | 2025-11-20 18:00:00 UTC | 0 | 0 | 0 |
| Nov 20, 18:00 | 2025-11-20 18:00:00 UTC | 2025-11-21 00:00:00 UTC | 0 | 0 | 0 |
| Nov 21, 00:00 | 2025-11-21 00:00:00 UTC | 2025-11-21 06:00:00 UTC | 0 | 0 | 0 |
| Nov 21, 06:00 | 2025-11-21 06:00:00 UTC | 2025-11-21 12:00:00 UTC | 0 | 0 | 0 |
| Nov 21, 12:00 | 2025-11-21 12:00:00 UTC | 2025-11-21 18:00:00 UTC | 0 | 0 | 0 |
| Nov 21, 18:00 | 2025-11-21 18:00:00 UTC | 2025-11-22 00:00:00 UTC | 0 | 0 | 0 |
| Nov 22, 00:00 | 2025-11-22 00:00:00 UTC | 2025-11-22 06:00:00 UTC | 0 | 0 | 0 |
| Nov 22, 06:00 | 2025-11-22 06:00:00 UTC | 2025-11-22 12:00:00 UTC | 0 | 0 | 0 |
| Nov 22, 12:00 | 2025-11-22 12:00:00 UTC | 2025-11-22 18:00:00 UTC | 0 | 0 | 0 |
| Nov 22, 18:00 | 2025-11-22 18:00:00 UTC | 2025-11-23 00:00:00 UTC | 0 | 0 | 0 |
| Nov 23, 00:00 | 2025-11-23 00:00:00 UTC | 2025-11-23 06:00:00 UTC | 0 | 0 | 0 |
| Nov 23, 06:00 | 2025-11-23 06:00:00 UTC | 2025-11-23 12:00:00 UTC | 0 | 0 | 0 |
| Nov 23, 12:00 | 2025-11-23 12:00:00 UTC | 2025-11-23 18:00:00 UTC | 0 | 0 | 0 |
| Nov 23, 18:00 | 2025-11-23 18:00:00 UTC | 2025-11-24 00:00:00 UTC | 0 | 0 | 0 |
| Nov 24, 00:00 | 2025-11-24 00:00:00 UTC | 2025-11-24 06:00:00 UTC | 0 | 0 | 0 |
| Nov 24, 06:00 | 2025-11-24 06:00:00 UTC | 2025-11-24 12:00:00 UTC | 0 | 0 | 0 |
| Nov 24, 12:00 | 2025-11-24 12:00:00 UTC | 2025-11-24 18:00:00 UTC | 1 | 1 | 0 |
What Hacker News says
2 sourcesShow HN: Dia2, open-weights TTS model for realtime speech to speech
Dia2 is an open-weights, streaming dialogue TTS model. It is capable of generating speech without a full sentence, making it suitable for low-latency speech-to-speech systems. It can generate up to 2 minutes of English audio, and supports audio prefixing.
The inference code and weights (1B / 2B variants) are uploaded to Github and Hugging Face with Apache 2.0 license, to accelerate research. This work was heavily influenced by KyutaiTTS, Mimi, and Sesame. We thank the TPU research cloud for providing computational resources.
3 points · Open discussion