devnen/Dia-TTS-Server

Self-host the powerful Dia TTS model. This server offers a user-friendly Web UI, flexible API endpoints (incl. OpenAI compatible), support for SafeTensors/BF16, voice cloning, dialogue generation, and GPU/CPU execution.

48
/ 100
Emerging

This project provides a straightforward way to turn written text into natural-sounding speech, especially for realistic conversations. You input text, optionally with speaker labels or example audio, and it produces high-quality audio recordings. Voice actors, content creators, and educators can use this to generate spoken content efficiently.

346 stars. No commits in the last 6 months.

Use this if you need to quickly and consistently generate natural-sounding speech from text, including multi-speaker dialogue, without complex setup or relying on external services.

Not ideal if you require a highly customized voice that goes beyond the provided voice cloning capabilities or if you prefer to build a text-to-speech system from scratch.

voice-generation content-creation dialogue-synthesis audiobook-production e-learning
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 21 / 25

How are scores calculated?

Stars

346

Forks

63

Language

Python

License

MIT

Last pushed

May 31, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/devnen/Dia-TTS-Server"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.