#aiaudio — Public Fediverse posts

China's Cigar-Shaped Rocket

It looks like a UFO.

http://john1126.com/787

#China #space #OmniVoice #AIAudio #UFO

Not all among us are human.

If you could hear God's voice, it might sound like this....

http://john1126.com/786

#AIAudio #Omnivoice #aliens #spiritual

https://winbuzzer.com/2026/07/23/sony-sues-udio-over-30117-recordings-in-new-ai-music-case-xcxwbn/

Sony has filed a separate lawsuit against AI music generator Udio identifying 30,117 recordings used for AI training after a previous ruling kept its larger catalog out of its first case.

#AI #Udio #Sony #AIMusic #GenAI #AITraining #AIAudio #AudioGeneration #Copyright #FairUse #MusicIndustry #YouTube

https://winbuzzer.com/2026/07/19/hacked-code-maps-sunos-alleged-music-scraping-pipeline-xcxwbn/

Shared hacked code details how Suno collected millions of music clips and lyrics, adding disputed scraping evidence to ongoing copyright litigation.

#AI #AIMusic #Suno #ContentScraping #DataScraping #AITraining #AIAudio #AudioGeneration #Copyright #FairUse

https://winbuzzer.com/2026/07/03/meta-caps-smart-glasses-audio-aid-in-paid-tier-test-xcxwbn/

Meta One Premium ties expanded Conversation Focus use on AI smart glasses to monthly caps, making local audio help a paid hardware-access issue for owners.

#AI #MetaInc #SmartGlasses #ConversationFocus #MetaOnePremium #AIAudio #AIHardware #AIDevices #Wearables #AIWearables

https://winbuzzer.com/2026/06/29/suno-spark-grants-pair-artist-support-with-speech-limits-xcxwbn/

Suno's Spark program offers independent artists grants and marketing support while its terms impose approval, disclosure, speech, and rival-tool limits.

#AI #SunoSpark #Suno #AIMusic #AIAudio #GenAI #MusicIndustry

Can you tell this voice is AI? It sounds very human to me.

Free tool used to generate audio: #Omnivoice on #Linux

This is the reading of Part II to the poem:
Muspilli

meaning "World's End"

(from the year 870 AD, originally written in Old German by anonymous)

Old High German is no longer used today in normal communications, but #AI could still translate it.

http://john1126.com/537

#German #OldGerman #poetry #poem #AIaudio #TextToSpeech #prophecy

AI is changing how content is created. Audio is changing how content is consumed. 🎙️.FM sits at the intersection of both. 🤖

Premium .FM domains are now live at auction through @namecheap: https://get.fm/auctions

🎧 Podcasts
🤖 AI Voice
📡 Streaming

#AIAudio #Podcasting #dotFM #VoiceAI #Ai #AIAgent

You type “Follow Me” every day. Now make it your brand. The smartest creator domains are short, memorable, and social-native.

That’s why .FM works. Follow Me @ https://Get.fm

#dotFM #FollowMe #CreatorEconomy #Creators #AIAudio #TikTokTips #TikTok #Instagram #Social

https://winbuzzer.com/2026/06/12/deezer-opens-free-ai-playlist-scanner-to-rival-services-xcxwbn/

Deezer has launched a free AI music detector for playlists on rival platforms, as AI generated tracks increasingly strain recommendations and royalties.

#AI #Deezer #AIMusic #AIGeneratedContent #GenAI #AIAudio #AudioGeneration #StreamingServices #Streaming #Spotify #MusicIndustry

Woman from 1962 TV commercial cloned to produce this audio in 2026! #OmniVoice #TTS #books #AIAudio

https://winbuzzer.com/2026/06/07/audio-interaction-voice-model-decides-when-to-stay-silent-xcxwbn/

Audio-Interaction is a new open-source voice model that knows when to stay silent by deciding every 0.4 seconds whether to answer or continue listening.

#AudioInteraction #StreamAudio2M #SoundFlow #AIAudio #OpenSourceAI #AIModels

Obama's Voice Cloned

MIT purposefully degraded their reproduction of Obama's voice, years ago, but now with publicly available, free AI tools, his voice (or any other voice) can be cloned without distortion.

Tool: #OmniVoice

http://john1126.com/763

#AIAudio #AI #spiritual #TTS

https://winbuzzer.com/2026/05/29/sesame-launches-iphone-voice-ai-app-with-four-agents-xcxwbn/

Sesame has put its hypereralistic conversational AI agents on iPhone, opening a public preview app that turns its research demo into a consumer product.

#AI #VoiceAI #ConversationalAI #VoiceAssistants #AIAgents #AIAssistants #AIAudio #AIVoices #AIVoiceGeneration #SpeechSynthesis

https://winbuzzer.com/2026/05/28/elevenlabs-launches-music-v2-for-mid-track-genre-shifts-xcxwbn/

ElevenLabs has launched its Music v2 AI music model that can switch genres within a track and regenerate selected sections while the company stresses licensed-data and commercial-use claims.

#AI #ElevenLabs #Music #AIMusic #AIAudio #AudioGeneration #GenAI

https://winbuzzer.com/2026/05/27/spotify-defends-licensed-ai-music-under-universal-deal-xcxwbn/

Spotify is publicly defending its licensed AI music strategy after setting up a Universal-backed covers and remixes product.

#AI #AIMusic #Spotify #GenAI #AIAudio #MusicIndustry #StreamingServices

https://winbuzzer.com/2026/05/25/stepfun-launches-stepaudio-25-for-live-voice-ai-xcxwbn/

Chinese AI lab StepFun has launched StepAudio 2.5 Realtime, an end-to-end live voice model for audio input and output in one system, withpersona control and paralinguistic understanding.

#AI #StepAudio25Realtime #StepFun #VoiceAI #AIModels #AIVoices #AIAudio

https://winbuzzer.com/2026/05/21/stability-ai-launches-stable-audio-30-for-developers-xcxwbn/

Stability AI has released Stable Audio 3.0 as an audio-model family that combines open-weight availability, licensed-data training, and longer music generation.

#AI #StableAudio25 #StabilityAI #AIAudio #AIMusic #AudioGeneration #GenAI #AIModels #OpenSourceAI

A new experiment at Andon.fm handed full control of streaming radio stations to AI models including ChatGPT, Claude, Gemini, and Grok. #Radio #AIAudio #AI #ChatGPT #Claude #Gemini #Grok #dotFM
https://www.insideradio.com/free/ai-chatbots-attempts-at-running-radio-stations-get-a-failing-grade/article_9550fb8c-bcc2-40ae-b67d-643a359844a6.html

https://winbuzzer.com/2026/05/17/openai-buys-ai-voice-startup-weights-xcxwbn/

OpenAI appears to have acquired Weights.GG for voice technology, talent and related assets.

#AI #OpenAI #WeightsGG #GenAI #AIAudio #AIVoices #AIVoiceGeneration #VoiceCloning #SpeechSynthesis

You type “Follow Me” every day. Now make it your brand. The smartest creator domains are short, memorable, and social-native.

That’s why .FM works. Follow Me @ https://Get.fm

#dotFM #FollowMe #CreatorEconomy #Creators #AIAudio #TikTokTips #TikTok #Instagram #Social

https://winbuzzer.com/2026/04/16/google-launches-gemini-31-flash-tts-for-developers-xcxwbn/

Google Launches Gemini 3.1 Flash TTS in Preview

#AI #Gemini31FlashTTS #GeminiAPI #Google #GoogleGemini #GoogleAI #GoogleAIStudio #GenerativeAI #AIModels #AIAudio #AIVoiceGeneration #SpeechSynthesis #VoiceCloning

🚨 .FM DROPS ARE LIVE 🚨 Don’t miss it → https://Get.fm/auction

The best names don’t get registered… They get sniped in auctions. Premium .FM domains just expired — now up for grabs via Namecheap

If you’re building:
🎧 Podcasts
🤖 AI voice agents
📡 Streaming platforms

This is where brands are born⚡ One name = your entire signal.

#dotFM #DomainNames #AIAudio #Startups #Branding #Auction

https://winbuzzer.com/2026/03/26/tencent-open-sources-covo-audio-7b-speech-language-model-xcxwbn/

Tencent Releases Covo-Audio Open-Source 7B Speech AI Model

#AI #Tencent #TencentAILab #CovoAudio #AIModels #AIResearch #AIAudio #AIVoiceGeneration #OpenSourceAI #SpeechSynthesis

https://winbuzzer.com/2026/03/25/google-launches-lyria-3-pro-ai-music-generation-model-xcxwbn/

Google's New Lyria 3 Pro AI Music Model Generates 3 Minute Tracks

#AI #Lyria3Pro #Lyria #Google #GenerativeAI #GoogleDeepMind #AIMusic #AIAudio #AudioGeneration #Music #GoogleVertexAI #GoogleAIStudio #BigTech #SynthID #Suno #Udio

https://winbuzzer.com/2026/03/12/gemini-embedding-2-unifies-text-images-video-in-one-model-xcxwbn/

Gemini Embedding 2 Unifies Text, Images, Video in One Model

#AI #Google #BigTech #GoogleGemini #EnterpriseAI #MultimodalAI #AISearch #AIAudio #AIVideo #AIImages #GoogleAI #GoogleDeepMind #GeminiEmbedding2

**ACE-Step** — фреймворк для генерации музыки на локальной машине
🎼 Треки до 4 хв за 20 сек
⚡️ В 15× швидше Suno AI
🎛️ Контроль жанру, тексту, ритму
🧠 Працює з 19 мовами
🎚️ Редагує існуючий аудіо
💻 A100 / 4090 / 3090 (мін. 16ГБ VRAM)
GitHub: [https://github.com/ace-step/ACE-Step](https://github.com/ace-step/ACE-Step)
\#MusicGen #AIaudio #OpenSource #LLM #GenAI #TextToMusic #LocalAI #RTX4090 #AItools #GeekStack #Python #cuda

**ACE-Step** — open-source фреймворк для генерации музыки “как у Suno”, только локально и без соплей.
⚙️ Жрёт текст, стиль, жанр, теги — выдаёт трек с нормальной мелодией, ритмом и даже гармонией.
🚀 До 4 минут звуку за ~20 секунд на A100. В 15 раз быстрее LLM-монстров.
🧩 Генерит, ремикширует, маскует, заменяет строки, делает вариации.
🧠 19 языков, включая русский.
🎧 От техно до оркестра — без лишних API-ключей и очередей.
🎮 Работает на A100 / 4090 / 3090, минимум 16 ГБ RAM, Python + CUDA.
👉 GitHub: https://github.com/ace-step/ACE-Step
#AIAudio #ACEstep #GenMusic #OpenSource #RTX4090 #CUDAcore #LLMsucks #SunoAlt #LocalStack #DevRig #GeekTools

ACE-Step — это не просто ещё один генератор музыки. Это *реальный прорыв в том, как ИИ превращается в инструмент*, а не в сервис по подписке. Почему это важно:
🚀 **1. Скорость, близкая к реальному времени**
4 минуты финализированного трека за ~20 секунд рендера — это уже не "ждать результат", а **генеративный live-loop**, как у музыканта в DAW.
Ни Suno, ни Udio, ни LLM-генераторы не дают такой latency. Здесь — практически instant feedback. Можно строить процесс продакшна как с сэмплером или synth engine.
🔧 **2. Полный контроль и редактируемость**
Возможность:
менять жанр и стиль без потери ритмики,
редактировать текст и фразы,
маскировать участки и встраивать новые — делает это **настоящим DAW-компаньоном**, а не просто "black-box генератором".
🧠 **3. Генеративная музыка стала **open-source**
Всё это — локально, open-source, без API ключей, лимитов и цензуры.
Это то, чего не было с MidJourney в графике и Suno/Udio в музыке: **независимый pipeline, разворачиваемый у себя**.
Ты можешь не просто использовать — ты можешь **встраивать, модифицировать, хакать**.
🎛️ **4. Это уже не игрушка — это production-ready**
19 языков, профессиональное звучание, управляемая структура и поддержка микса/мастеринга.
Подходит для:
синтезаторов с AI backend’ом,
генерации треков под видео, игры, фон, рекламу,
авто-написания демо, подкастов, фоновых саундтреков.
🧬 **5. Это новая веха: генеративный ИИ стал инструментом, а не платформой**
Переход от модели-сервиса к **модели-библиотеке**.
Это как сравнивать Google Translate и локальную модель для встраивания в продукт.
Это shift: **LLM-мозг** + **DAW-интеграция** + **музыкальная интерактивность** = новое поколение ПО для творчества.
ACE-Step — это та точка, после которой "ИИ делает музыку" уже не метафора, а **новый workflow**.
Без ограничений. Без посредников. Без лагов. У тебя на GPU.
Хэштеги:
**#GenerativeAI #AIinMusic #OpenSourceMusic #TextToAudio #AIProducer #RealtimeAudioAI #DAWnextgen #LLMsound #AceStep **#aitools

соус: https://bastyon.com/post?s=874313bd495fac0ae7aae33a9d3bee79f8f1d9f902bceb34f254da0d6eb2b33d&ref=PMC55eKCrsxoJNkiB3f71AgFLQC3T9HkWV