Dia
A TTS model capable of generating ultra-realistic dialogue in one pass.
Dia scores 4.5/10 (Emerging) in Voice & Realtime.
Language Python License Apache-2.0 Stars 19.3k★ Type model Self-host Yes Repo nari-labs/dia Homepage https://github.com/nari-labs/dia
Quality
Emerging 4.5
Adoption 57
Activity 5
Maturity 65
Community 57
Capability 50
Show the math
Overall 4.5/10
value = 4.5/10
score = value
Adoption 6.1/10
value = 57.2/100
score = 1 + 9 * value / 100
Activity 1.4/10
value = 5/100
score = 1 + 9 * value / 100
Maturity 6.8/10
value = 64.6/100
score = 1 + 9 * value / 100
Community 6.1/10
value = 56.7/100
score = 1 + 9 * value / 100
Capability 5.5/10
value = 50/100
score = 1 + 9 * value / 100
Key metrics
19.3k★ GitHub stars
0/90d Recent commits
0 devs/90d Recent contributors
1.2y Project age
8mo ago Last commit
Gotchas
No gotchas documented yet. Contribute one if you know a constraint we missed.
Labels
- Self-hosted
Self-hosted
You deploy and operate it yourself; there is no hosted option here.
tts dialogue multi-speaker nonverbal realistic