gmltmd789/UnitSpeech
An official implementation of "UnitSpeech: Speaker-adaptive Speech Synthesis with Untranscribed Data"
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.
Stars
138
Forks
15
Language
Jupyter Notebook
License
—
Category
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.
Higher-rated alternatives
TensorSpeech/TensorFlowTTS
:stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for...
lucasnewman/nanospeech
A simple, hackable text-to-speech system in PyTorch and MLX
Tomiinek/Multilingual_Text_to_Speech
An implementation of Tacotron 2 that supports multilingual experiments with parameter-sharing,...
keonlee9420/STYLER
Official repository of STYLER: Style Factor Modeling with Rapidity and Robustness via Speech...
jxzhanggg/nonparaSeq2seqVC_code
Implementation code of non-parallel sequence-to-sequence VC