Speaches
Self-hosted OpenAI-API-compatible speech server bundling faster-whisper STT and Kokoro/Piper TTS with a realtime WebSocket endpoint.
Speaches scores 5.4/10 (Solid) in Voice & Realtime.
Language Python License MIT Stars 3.4k★ Type service Self-host Yes Repo speaches-ai/speaches Homepage https://speaches.ai
Quality
Solid 5.4
Adoption 38
Activity 41
Maturity 91
Community 41
Capability 50
Show the math
Overall 5.4/10
value = 5.4/10
score = value
Adoption 4.5/10
value = 38.4/100
score = 1 + 9 * value / 100
Activity 4.7/10
value = 40.8/100
score = 1 + 9 * value / 100
Maturity 9.2/10
value = 91.3/100
score = 1 + 9 * value / 100
Community 4.7/10
value = 41.1/100
score = 1 + 9 * value / 100
Capability 5.5/10
value = 50/100
score = 1 + 9 * value / 100
Key metrics
3.4k★ GitHub stars
12/90d Recent commits
1 devs/90d Recent contributors
2.1y 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.
- Managed option
Managed option
Available as a hosted/managed service in addition to self-hosting.
self-hosted stt tts openai-compatible realtime