X-LANCE/UniCATS-CTX-txt2vec

[AAAI 2024] CTX-txt2vec, the acoustic model in UniCATS

29
/ 100
Experimental

This project helps create highly natural-sounding, contextually aware spoken audio from written text. It takes a text input and a short audio 'prompt' to set the tone and speaking style, then generates high-quality audio that seamlessly continues the prompt's voice. This is ideal for researchers and developers working on advanced text-to-speech (TTS) systems where consistent voice and fluent context are crucial.

No commits in the last 6 months.

Use this if you need to generate speech that precisely matches a given voice and context, for applications like AI assistants, audiobook narration, or character dialogue in games.

Not ideal if you need a simple, off-the-shelf text-to-speech solution without requiring fine-grained control over voice context or if you are not comfortable with multi-step model training and external vocoding.

text-to-speech voice-synthesis audio-generation speech-research generative-AI
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

64

Forks

8

Language

Python

License

Last pushed

Nov 18, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/X-LANCE/UniCATS-CTX-txt2vec"

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