taresh18/TTSizer

πŸŽ™οΈ Automatically transcribe audio/video into high-quality, speaker-specific Text-To-Speech datasets ✨

43
/ 100
Emerging

This tool helps content creators, educators, or media producers automatically create high-quality datasets for Text-To-Speech (TTS) applications. You input raw video or audio files, and it produces perfectly aligned audio segments with corresponding text transcripts, specifically separated by speaker. This is ideal for anyone looking to generate synthetic voices from existing media for voiceovers, e-learning content, or character voices.

135 stars. No commits in the last 6 months.

Use this if you need to transform hours of audio or video content into structured datasets of speaker-specific voice clips and their exact text, without manual transcription and segmentation.

Not ideal if you only need a basic transcript of an audio file or if your media files do not contain spoken language.

voice-synthesis content-production media-transcription e-learning-development audio-engineering
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 16 / 25

How are scores calculated?

Stars

135

Forks

19

Language

Python

License

Apache-2.0

Last pushed

Aug 10, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/taresh18/TTSizer"

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