Ethan B. Holland

Over 56,600 manually organized AI links and counting

AI Audio News: Week Ending 02/09/2024

February 25, 2024

AI Audio

“The Whisper Audio API now supports word-level timestamps! With the new `timestamp_granularities` parameter, you can get word-level precision for transcripts and video edits. https://t.co/aON96JKlkk https://t.co/sinyl77ypS” / X – https://twitter.com/OpenAIDevs/status/1756038953529147826

Stability.ai – Natural language guidance of high-fidelity text-to-speech models with synthetic annotations – https://www.text-description-to-speech.com/

Natural language guidance of high-fidelity text-to-speech models with synthetic annotations – YouTube – https://www.youtube.com/watch?v=akBy6zrMGK0&t=5s

“Introducing ElevenLabs GPT, my latest custom GPT that brings any prompt to life with a realistic voice! 🗣️ You can: – generate an audiobook with one prompt! – have online articles read to you – listen to any docs you upload Watch the demo below to see it in action! 🚀 https://t.co/i8Zw8U1iGW” / X – https://twitter.com/ammaar/status/1752745588561740037

“Stable Audio released a new model called AudioSparx 1.0. The new model is capable of creating long-form music with a more varied structure than competing models. And of course, it’s open-sourced. https://t.co/qa60GscU5H” / X – https://twitter.com/rowancheung/status/1755789569704804679

An early look our AI Music experiment – YouTube Blog – https://blog.youtube/inside-youtube/ai-and-music-experiment/

“We’ve released our full paper on on the Stable Audio model 💿 arXiv: https://t.co/2ML8hlDBVK Code: https://t.co/HuuOj8cyTC… Metrics: https://t.co/QZJEEXXJn9 Demo: https://t.co/c5nh7lHvbI… 🧵 https://t.co/ACjdWRTAha” / X – https://twitter.com/stableaudio/status/1755558334797685089

“Presenting MetaVoice-1B, a 1.2B parameter base model for TTS (text-to-speech). * Emotional speech in English * Voice cloning with fine-tuning * Zero-shot cloning for American & British voices * Support for long-form synthesis https://t.co/35dTjbUvU2 https://t.co/mKpUYtd5qo https://t.co/vzHFp0k9DX” / X – https://twitter.com/metavoiceio/status/1754983953193218193

MetaVoice-1B is a 1.2B parameter base model trained on 100K hours of speech for TTS (text-to-speech). It has been built with the following priorities:

metavoiceio/metavoice-1B-v0.1 · Hugging Face – https://huggingface.co/metavoiceio/metavoice-1B-v0.1

[2402.04229] MusicRL: Aligning Music Generation to Human Preferences – https://arxiv.org/abs/2402.04229

AI can now master your music—and it does shockingly well | Ars Technica – https://arstechnica.com/ai/2024/02/mastering-music-is-hard-can-one-click-ai-make-it-easy/

Be Sure To Read “This Week In AI”

This week’s executive overview and top links are here:

AI News #19: Week Ending 02/02/2024 with Executive Summary and Top 18 Stories

The post you just read is an extension of my weekly newsletter, This Week In AI, an executive summary of the top things to know in AI. Each week, I create an accessible overview for laypeople to feel confident they are conversant with the week’s AI developments. I include a curated list of must-click links of the week, to offer everyone a hands-on opportunity to explore the most intriguing updates in artificial intelligence across various categories, including robotics, imagery, video, AR/VR, science, ethics, and more. Beyond the overview, I post these topic-based deeper dives (below). If you haven’t read this week’s overview, I recommend starting there.