Dossier
voice synthesis
Coverage of voice synthesis in the Nexus archive.
- Inflect-Micro-v2: complete voice in 9.36M parameters
Inflect-Micro-v2 is a voice synthesis model with 9.36 million parameters, available on Hugging Face. The article links to its model page and Hacker News discussion with 10 points and one comment.
- The only way to fight deepfakes is by making deepfakes
The article describes an experiment where a person used a deepfake voice to call their parents, who quickly recognized the artificial nature of the voice. The author suggests that creating deepfakes to combat their misuse may be a necessary strategy.