Emotional-Text-to-Speech/hmm-for-emo-tts

:computer: A repository with comprehensive instructions for using the Festvox toolkit for generating Emotional speech :speaker: from text

41
/ 100
Emerging

This project offers clear instructions for creating speech from text with specific emotional tones. It takes written text and a collection of audio recordings of a speaker expressing different emotions, then generates audio of that speaker saying the text with a chosen emotion. It's designed for language researchers, voice developers, or content creators who need to produce synthetic speech with nuanced emotional expression.

No commits in the last 6 months.

Use this if you need to build custom text-to-speech voices that can convey specific emotions like anger, happiness, or sadness for applications like interactive voice assistants, narrated content, or educational tools.

Not ideal if you need a simple, off-the-shelf text-to-speech solution without custom emotional training or if your primary goal is general-purpose voice generation without specific emotional control.

speech synthesis emotional AI voice development audio content creation linguistics research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

50

Forks

10

Language

CSS

License

MIT

Last pushed

Dec 30, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/Emotional-Text-to-Speech/hmm-for-emo-tts"

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