Best Audio AI Models
8 models tracked · 60 recent news stories
Most-talked-about Audio right now
Ranked by mentions across 30+ AI sources in October 2026.
GPT-Live-1 is OpenAI's full-duplex voice model, which can listen and speak at the same time. OpenAI introduced it as GPT-Live on July 8, 2026, powering ChatGPT's upgraded voice mode, and opened it to developers in the API on September 10, 2026 at $0.05 per minute for the voice layer. The model handles the conversation itself — turn-taking and back-channel cues — and hands the reasoning to a separate model the developer chooses.
Gemini 3.8 Live is Google's real-time voice model, released on September 15, 2026 together with a Gemini 3.8 Live Extended Thinking variant. Google calls them its most advanced live dialogue models: they run tool and API calls in the background while the conversation continues, understand what the camera sees and support 97 languages. Both are available in the Gemini API, Google AI Studio and Gemini Enterprise, and Gemini 3.8 Live now powers Search Live in the Google app.
Lyria 3 helps you express, explore, and experiment with high-fidelity music, using prompts to create tracks with natural flow from note to note.
Mureka V9.5 is the AI music generation model from Mureka, the music platform of China's Kunlun Tech, introduced in July 2026. Kunlun pitches it as making songs that sound less machine-made by using "reflective reasoning" and agentic song creation, and in August 2026 Mureka launched it internationally alongside a second music model called O3.
Suno v6 is the AI music generation model Suno released on September 9, 2026 — its first model built with support from the record industry, following partnerships with Warner Music and BMG. Suno says v6 was trained from the ground up on a new, licensed dataset rather than the music used for earlier versions, and it replaces the retiring v4.5 and v5 models as the company faces a wave of copyright lawsuits.
Udio's text-to-music model generates complete songs — vocals, lyrics and backing instrumentation — from a natural-language prompt.
OpenAI's speech-to-text AI model
21 sources
📰 Latest Audio Model News(60 stories)
Psychology says children who whisper to their toys may be practising an important real-life skill without
Your Voice Agent Transcribes the Wrong Person: I Measured It
by Sebastian Buzdugan — I played two people talking at once into Whisper 80 times.
![[AI Consciousness / Post-Punk, Darkwave] The Pulse Is Missing — HAL_9001](https://wsrv.nl/?url=https%3A%2F%2Fpreview.redd.it%2Fketl5hd404sh1.jpeg%3Fwidth%3D640%26crop%3Dsmart%26auto%3Dwebp%26s%3D9113e2e6065f7c8f87216a302e1f66b2315ac0f2&w=800&h=384&fit=cover&output=webp&q=75&il=)
Ray BEAMS Unlocks Salomon's Sweet Tooth With the XT-Whisper “Cherry Cake Party”
4 sources
Brian Doerksen’s Song ‘Whisper’ Arrives Ahead of Posthumous Final Album
Whisper it quietly: have Greggs shares FINALLY turned the corner?
Whisper Web3 Super-App to Reveal New Ecosystem Plans at Korea Blockchain Week
How eight hours of studio audio cut Whisper tiny’s errors by 27%
A small model, a language variety it had never really heard, and a dataset built the slow way. Continue reading on Medium »
![[Aggressive Liquid DnB] Leaves Overgrown - DrEDGE ARCADiA [Official Lyric Video]](https://wsrv.nl/?url=https%3A%2F%2Fexternal-preview.redd.it%2F9tTxBiAuMiNGAp6H04maQ1_vekGS0S3wdvaVgf0V89g.jpeg%3Fwidth%3D320%26crop%3Dsmart%26auto%3Dwebp%26s%3D3ecf39b43778f8b6dfd857de9081fe0bb1265c01&w=800&h=384&fit=cover&output=webp&q=75&il=)
FP Movement Debuts New Salomon Partnership with XT-6 and XT-Whisper Collabs
Over 100 Names, Rape Claims: Inside Silicon Valley's Secret 'Whisper Network'
3 sources
The Whisper of Muse: We Are Already on the Eve of the Collapse and Reconstruction of the Internet Business Model
'Whisper network' warns women of 'over a 100' sexual predators at AI epicentre: Report
![[Rock Opera /Suno Studio] Ode To Bruce Wayne by Arthur Wegley (ARed)](https://wsrv.nl/?url=https%3A%2F%2Fpreview.redd.it%2F8pq0rv2414sh1.jpeg%3Fwidth%3D640%26crop%3Dsmart%26auto%3Dwebp%26s%3Ddcaa8a7c6d3b5b5504bd3548acec6d68d4e19a3e&w=800&h=384&fit=cover&output=webp&q=75&il=)
“Whisper Fringe” Is the Low-Maintenance Fall Hair Refresh You’ve Been Looking For
2 sources
