Every week, I organize 400 to 700 links into roughly 60 categories as part of my ongoing effort to learn about AI. This is my personal notebook, which I enjoy sharing with friends… a hobby and a labor of love, rather than a commercial publication or product.
If you arrived here through a search or shared link, this page collects the links I found for Audio for the week ending September 4, 2026.
As part of my learning process, I like to automate the category covers. It gives me a chance to learn Python and APIs.
This week’s cover prompt was written using Claude Opus 4.7, and the image was generated using Nano Banana 2.1.
Category Cover Image Prompt: Psychedelic screen-printed gig poster of a vintage ribbon microphone melting into concentric swirling sound waves that bloom into autumn leaves and spiraling vinyl grooves around a harvest moon, electric magenta, acid orange, deep teal and lime green inks on cream paper with visible registration offset, bold hand-lettered 'Audio' arcing above the mic in ornate 1960s Fillmore-style psychedelic letters, intricate op-art border, flat ink layers, vertical composition.
This Week in Audio News
Summary by Claude Sonnet 5.5 based on this week’s links:
- Speech-to-text price and speed race: Microsoft AI says MAI-Transcribe-2 is the fastest, cheapest and most accurate speech recognition model, claiming 10x the speed of GPT-Transcribe. Google shipped Gemini 3.5 Transcribe the same week, so transcription is clearly a contested space.
- Meta's real-time Muse Voice Transcribe: Meta Superintelligence Labs introduced Muse Voice Transcribe as its first real-time audio perception model. Meta says it handles streaming transcription, diarization for 20+ speakers and endpointing in one model, with code-switching across languages.
- Voice as an interface: Bilawal Sidhu showed voice commands steering God's Eye View, from checking rush-hour traffic to asking about military flights in a region. Ethan Mollick found Codex voice magical when it works, but reported it switches threads and accesses the rest of Codex inconsistently.
This summary was generated by Claude Sonnet 5.5 to help you explore the links below. Rest assured, I select, organize, and check the links by hand in Google Sheets, and write the introduction and personal commentary in The Main Newsletters myself each week as a labor of love.
This week's links related to Audio
My first “holy shit” moment with GPT-6 Astra: I asked it to create a world in Unreal Engine, and fill it with humans (each an Astra-powered agent) who all have to work together to survive. A day later, I was in my bedroom and heard voices coming from the living room… I
https://x.com/mattshumer_/status/2095596175705399482
Using voice mode to monitor rush hour traffic in God’s Eye View. It uses aggregated location data from TomTom to visualize how busy every road segment is. And in cities like Austin and London you can look at public CCTV cameras to confirm the actual conditions on the ground.
https://x.com/bilawalsidhu/status/2093333780719337873
🎬Video generation faster than playback! 🚀MiniMax H3 on vLLM-Omni + FastVideo’s FastH3: a complete 10.1s MP4 – video AND synchronized audio – rendered in 8.7s!⚡️ Thanks to @MiniMax_AI for the great Minimax H3 release, the FastVideo team @haoailab for open-sourcing FastH3 and
https://x.com/vllm_project/status/2094849929487552663
Muse Voice Transcribe is MSL’s first real-time audio perception model — rolling out today. SOTA in streaming speech-to-text, it handles speaker diarization, and endpointing natively in a single model.
https://x.com/finkd/status/2094836602681938385
Sam Altman on the Sources Podcast: OpenAI ‘will definitely do humanoids.’ It lines up with OpenAI’s actual moves: • It’s been building an in-house robotics team, with 33 roles currently open in SF, spanning actuator design, data-acquisition ops and embodied AI. • OpenAI
https://x.com/TheHumanoidHub/status/2095208025678315937
Microsoft AI’s MAI-Transcribe-2 undercuts OpenAI, Google and ElevenLabs on price and speed | VentureBeat
https://venturebeat.com/infrastructure/microsoft-ais-mai-transcribe-2-undercuts-openai-google-and-elevenlabs-on-price-and-speed
You can now use up to 14 references in your videos. Images, voices, character references, and more. Use “@” to tag each reference in your prompt.
https://x.com/imagine/status/2095249317875622255
Introducing Muse Voice Transcribe | Meta AI Research
https://research.meta.ai/blog/introducing-muse-voice-transcribe
Introducing Muse Voice Transcribe, the first real-time audio perception model from Meta Superintelligence Labs. Muse Voice Transcribe delivers real-time streaming ASR, diarization with 20+ speakers, and endpointing. It’s multilingual with seamless code-switching and improves
https://x.com/AIatMeta/status/2094839236016976028
MAI-Transcribe-2 is the fastest, most accurate and cheapest speech recognition model in the world | Microsoft AI
https://microsoft.ai/news/mai-transcribe-2-is-the-fastest-most-accurate-and-cheapest-speech-recognition-model-in-the-world/
Codex voice (or is it ChatGPT Work in Codex voice?) is magical when it works well, but has a lot of weird loose edges that make it hard to use, like it seems to constantly switch threads it is working on, multitasks only sometimes, accesses the rest of Codex inconsistently, etc.
https://x.com/emollick/status/2095340390731940317
Wan 3.0 debuts at #1 on the Artificial Analysis Video Editing Leaderboard, and is a close #2 in Text to Video with Audio Wan 3.0 is Alibaba’s new all-in-one video generation and editing model, positioned as a single system for turning multimodal creative direction into video. It
https://x.com/ArtificialAnlys/status/2095349174799888760
Complaint – #1 in Sony Music Publishing (US) LLC v. Anthropic PBC (N.D. Cal., 5:26-cv-09217) – CourtListener.com
https://www.courtlistener.com/docket/74720572/1/sony-music-publishing-us-llc-v-anthropic-pbc/
We are sharing a major update to our General World Models efforts. GWM Worlds 2 can generate full, interactive, real-time video simulations in one continuous 720p stream at 24 fps and audio at 48000 Hz, responding to your inputs as you explore. It is the first world model that
https://x.com/c_valenzuelab/status/2095548906281042144
God’s Eye View is on GitHub Trending. MIT license. Use voice commands to “jump into the cockpit of the nearest helicopter or jet” or ask “how many military flights are in this region” Turning the 3d globe into a canvas you can annotate w/ voice is really quite fun.
https://x.com/bilawalsidhu/status/2093693183976759387
Episode #1 of Nuro’s new podcast, Unsupervised with @dfergusonnz, goes live tomorrow! His first guest is @aurora_inno’s @chris_urmson, a long-time friend and former colleague at CMU and Google’s Self-Driving Car Project. Tune in tomorrow:
https://x.com/nuro/status/2094802469947613643
Fastest. Cheapest. Best. … MAI-Transcribe-2 10x faster than GPT-Transcribe. 5x faster than Gemini 3.5 #1 on the Artificial Analysis accuracy-latency Pareto frontier Priced at the lowest on the market. Truly fantastic work from the team! Try it out below.
https://x.com/mustafasuleyman/status/2095521337670312056
Open development helps AI move faster. When we can learn from, build on and improve each other’s work, we can make better technology together. Hear @ctnzr on the MAD Podcast with @mattturck
https://x.com/nvidia/status/2093457336161419676
Here’s what launched this week: … Gemini 3.5 Transcribe, our most precise speech-to-text model yet, designed to deliver intelligent transcriptions … Gemini Omni 1.1 Flash, bringing expanded creative capabilities and controls for video generation and editing … @GeminiApp’s Live
https://x.com/GoogleAI/status/2093356767992279503
Aside from waiting for economic impact, we are now at the place where AI video, image & music models are good enough to be real tools for letting more people who never could produce new kinds of art How long until we see a creativity boom among the slop flood? Is it happening?
https://x.com/emollick/status/2093362761925284279
kausable is building AI systems that can adapt when the world changes. Next week I have @JohannesHaux, co-founder and CEO of kausable, on the podcast. They are building in Heidelberg, right in the wider @Cyber_Valley ecosystem. And with Cyber Valley turning 10 on September 9,
https://x.com/IlirAliu_/status/2093972489823269073
In this week’s Digiday Podcast episode, hosts Kimeko McCoy and Tim Peterson recap the season’s biggest developments in the media and marketing industries and the questions they raise for the final stretch of 2026.
https://x.com/Digiday/status/2094734538047909911
The full podcast lineup returns next week! On Tuesday, @FrankReig, CEO of @VolterAPower joins The Road to Autonomy. Friday, an all new Autonomy Singals with @RobGsix presented by @KPMG. Saturday, Autonomy Markets with @WaltLightShed.
https://x.com/RoadToAutonomy/status/2093512711544222181
Unsupervised Episode 1 with @aurora_inno’s @chris_urmson is now available on Spotify! Listen to the full podcast in the Spotify app:
https://t.co/5FwETOBDR3 #unsupervisedpodcast #selfdriving #autonomousvehicles
https://x.com/nuro/status/2095527239240515862
The Telegraph is expanding its video podcast strategy into franchises spanning events and paid memberships to deepen audience relationships.
https://x.com/Digiday/status/2094372158185087043
Photon 2.1 is out, adding text-to-speech models and B200 support to our realtime multimodal inference engine.
https://x.com/vikhyatk/status/2095230035707977947
Leave a Reply