Subculture Science Research Group's Blog
  • Blog
  • Portfolio
  • About us
  • Tags
  • 日本語
Subculture Science Research Group's Blog

Whisper


Reading Aloud in My Own Voice: Voice-Clone TTS from 30 Seconds of Audio

 Posted on Sun Nov 15 2026  |  3 min  |  1228 words  |    • Other languages: 日本語

Ready-made TTS reads text well but never in your voice. Here is how a reference clip of about 30 seconds becomes a registered voice you can call over HTTP, using TADA and FastAPI. [Read More]
TTS  voice cloning  FastAPI  Whisper  problem solving 

A Japanese Voice-Clone TTS Pipeline with TADA, FastAPI, Whisper, and FFmpeg

 Posted on Sun Nov 15 2026  |  6 min  |  1266 words  |    • Other languages: 日本語

How a reference-audio voice-clone TTS is built with TADA 3B-ML, FastAPI, Whisper, and FFmpeg: registration in a CLI, generation in a server, and why prompt.pt is passed between them. [Read More]
TTS  TADA  FastAPI  Whisper  FFmpeg  engineering 

 • © 2026  •  Subculture Science Research Group's Blog

Hugo v0.142.0 powered  •  Theme Beautiful Hugo adapted from Beautiful Jekyll

  • 日本語
  • English