- Microsoft’s new AI can simulate anyone’s voice with 3 seconds of audio Text-to-speech model can preserve speaker's emotional tone and acoustic environment. https://arstechnica.com/information-technology/2023/01/microsofts-new-ai-can-simulate-anyones-voice-with-3-seconds-of-audio/?comments=1&comments-page=3 1293 comments technology
Linked pages
- Meta’s AI-powered audio codec promises 10x compression over MP3 | Ars Technica https://arstechnica.com/information-technology/2022/11/metas-ai-powered-audio-codec-promises-10x-compression-over-mp3/ 298 comments
- LibriVox | free public domain audiobooks https://librivox.org/ 295 comments
- US acceptance of COVID vaccines rises, now like other Western democracies | Ars Technica https://arstechnica.com/science/2023/01/us-acceptance-of-covid-vaccines-rises-now-like-other-western-democracies/ 229 comments
- VALL-E https://valle-demo.github.io/ 151 comments
- FAA giving airlines another year to fix altimeters that can’t handle 5G signals | Ars Technica https://arstechnica.com/tech-policy/2023/01/faa-proposes-feb-2024-deadline-for-airplane-altimeters-to-filter-out-5g-signals/ 54 comments
- https://arxiv.org/abs/2301.02111 15 comments
- OpenAI upgrades GPT-3, stunning with rhyming poetry and lyrics | Ars Technica https://arstechnica.com/information-technology/2022/11/openai-conquers-rhyming-poetry-with-new-gpt-3-update/ 7 comments
- With Koe Recast, you can change your voice as easily as your clothing | Ars Technica https://arstechnica.com/information-technology/2022/09/with-koe-recast-you-can-change-your-voice-as-easily-as-your-clothing/ 1 comment
- Darth Vader’s voice will be AI-generated from now on | Ars Technica https://arstechnica.com/information-technology/2022/09/james-earl-jones-signed-darth-vader-voice-rights-to-disney-for-ai-use/ 0 comments
Related searches:
Search whole site: site:arstechnica.com
Search title: Microsoft’s new AI can simulate anyone’s voice with 3 seconds of audio | Ars Technica
See how to search.