Chatterbox
SoTA open-source TTS
Chatterbox scores 6.2/10 (Solid) in Voice & Realtime.
Language Python License MIT Stars 25.4k★ Type model Self-host Yes Repo resemble-ai/chatterbox Homepage https://github.com/resemble-ai/chatterbox
Quality
Solid 6.2
Adoption 60
Activity 40
Maturity 83
Community 64
Capability 64
Show the math
Overall 6.2/10
value = 6.2/10
score = value
Adoption 6.4/10
value = 60.1/100
score = 1 + 9 * value / 100
Activity 4.6/10
value = 40.2/100
score = 1 + 9 * value / 100
Maturity 8.5/10
value = 83.4/100
score = 1 + 9 * value / 100
Community 6.7/10
value = 63.7/100
score = 1 + 9 * value / 100
Capability 6.7/10
value = 63.7/100
score = 1 + 9 * value / 100
Key metrics
25.4k★ GitHub stars
2/90d Recent commits
2 devs/90d Recent contributors
63.75% preferred Blind human preference vs ElevenLabs (TTS quality) In a Resemble AI / Podonos blind listening evaluation, 63.75% of listeners preferred Chatterbox over ElevenLabs on audio quality and emotion. Not an error-rate metric; value is the raw preference rate. Source: Resemble AI (https://www.resemble.ai/learn/models/chatterbox).
1.2y Project age
active 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 voice-cloning low-latency emotion mit