ubisoft/ubisoft-laforge-daft-exprt
Daft-Exprt: Robust Prosody Transfer Across Speakers for Expressive Speech Synthesis
This project helps speech synthesis professionals create natural-sounding, expressive speech. You provide text and an audio sample of a speaker whose prosody (intonation, rhythm, stress) you want to emulate. The system then generates new speech in a target voice, using the expressive style from your audio sample. This is ideal for voice artists, game developers, or content creators needing highly customizable and emotionally rich synthetic voices.
129 stars. No commits in the last 6 months.
Use this if you need to transfer the expressive speech patterns from one voice to a different synthesized voice, allowing for consistent emotional delivery across various characters or narration styles.
Not ideal if you only need basic text-to-speech without complex emotional or prosodic transfer, or if you require direct voice cloning without the ability to manipulate prosody independently.
Stars
129
Forks
24
Language
Python
License
Apache-2.0
Category
Last pushed
Apr 08, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/ubisoft/ubisoft-laforge-daft-exprt"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
index-tts/index-tts
An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
stepfun-ai/Step-Audio-EditX
A powerful 3B-parameter, LLM-based Reinforcement Learning audio edit model excels at editing...
lucasnewman/f5-tts-mlx
Implementation of F5-TTS in MLX
unilight/seq2seq-vc
A sequence-to-sequence voice conversion toolkit.
FireRedTeam/FireRedTTS
An Open-Sourced LLM-empowered Foundation TTS System