the-bird-F/Expressive-Vectors
[ICASSP 2026] Task Vector in TTS: Toward Emotionally Expressive Dialectal Speech Synthesis
This project helps speech technologists create AI voices that speak in specific regional dialects with particular emotions. By inputting text and selecting a desired dialect and emotion, it produces natural-sounding expressive speech. This tool is designed for researchers or developers working on text-to-speech systems for diverse linguistic and emotional communication.
Use this if you need to generate high-quality synthetic speech that captures both the nuances of regional dialects and specific emotional tones without needing jointly labeled dialectal and emotional data.
Not ideal if you need a general-purpose text-to-speech system for standard languages or if you are not working with dialectal or emotional speech synthesis.
Stars
38
Forks
1
Language
Python
License
—
Category
Last pushed
Dec 24, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/the-bird-F/Expressive-Vectors"
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