gmltmd789/UnitSpeech

An official implementation of "UnitSpeech: Speaker-adaptive Speech Synthesis with Untranscribed Data"

39
/ 100
Emerging

This tool helps create custom, synthetic speech in any voice using a small audio sample. You provide a short reference audio of the voice you want to replicate and the text you want spoken (or another audio file for voice conversion). The output is a new audio file where the specified text is spoken in the voice from your reference audio. This is ideal for content creators, podcasters, or anyone needing to generate speech that matches a particular speaker's voice.

138 stars. No commits in the last 6 months.

Use this if you need to generate new speech or convert existing speech into a specific voice, even if you only have a short audio sample of that voice and no transcript.

Not ideal if you require extremely long-form audio generation without any slight degradation in quality, or if you need to use the generated audio for legally sensitive applications without clear disclosure.

audio-content-creation podcast-production voice-over synthetic-media digital-voice-cloning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

138

Forks

15

Language

Jupyter Notebook

License

Last pushed

Aug 17, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/gmltmd789/UnitSpeech"

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