sayzardITmedia NEWS (@itmedia_news)
Spotify가 AI 생성 오디오 콘텐츠를 저장할 수 있는 CLI 도구 'Save to Spotify'를 출시했습니다. AI 오디오 워크플로우와 음악 플랫폼 연동을 간소화하는 실용적인 개발자용 도구로 보입니다.
Winbuzzerhttps://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
セレスティア学園長 (@owata_aiart)
AI 음성 합성 도구 GPT-SoVITS와 Irodori-TTS를 비교한 결과, 감정 표현력에서는 Irodori-TTS가 크게 뛰어났다고 전했다. 음성 생성 모델의 성능 비교로, TTS 개발자와 크리에이터에게 참고가 될 만한 내용이다.
dotFM® | .FM Top Level Domain🚨 .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.
digilabKI in der frühen Kindheit
Elternbildung neu denken!
Starte den nächsten Elternabend oder KI-Workshop mit einem themenzentrierten Song
Lyria 3, der Musikgenerator von Gemini, ist seit Kurzem in Gemini integriert. Du kannst ihn direkt über den Chat nutzen, um themenzentrierte Songs zu generieren. (+ Musik erstellen)
#musikgenerator, #lyria3, #kisongserstellen, #aiaudio, #kiaudio, #KImusikunterricht, #kikompetenz, #lernenmitki, #kiimunterricht, #kreativmitmedien
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
PsychoticSheepToday I tested MusicGen, a music generation AI developed by Meta.
The model can create short music clips directly from text prompts such as "heavy metal with distorted guitars" or "lofi hip hop with piano and rain". Everything in this demo runs completely locally on my Linux system using my RX 6700 XT.
Setting it up is tricky because MusicGen is tightly pinned to old PyTorch versions. You need to manually install most dependencies and then install MusicGen itself with "--no-deps" to avoid overwriting your (ROCm-)PyTorch setup.
MusicGen is part of Meta’s AudioCraft project and generates audio by predicting compressed audio tokens instead of raw waveforms. The generated tracks often sound quite generic, which is a known limitation of current AI music models. Still, it can be useful for quickly prototyping ideas, generating background music, creating sound textures, or experimenting with AI-generated audio.
The results can also be improved by generating continuations of the audio multiple times. By extending the output step by step it is possible to create longer pieces of music of two to three minutes that develop more structure than the short clips shown here.
Video workflow:
- Recorded with OBS
- Edited in Kdenlive
- Transcoded with VAAPI (H.264)
No cloud, real hardware.
Everything runs on Linux, so anyone can set this up.
No GPU? No problem, you can also run it using PyTorch’s CPU backend, just much slower.
#AI #MachineLearning #MusicGen #GenerativeAI #AIaudio #OpenSource #Linux #LocalAI #Fediverse #Tech
The model can create short music clips directly from text prompts such as "heavy metal with distorted guitars" or "lofi hip hop with piano and rain". Everything in this demo runs completely locally on my Linux system using my RX 6700 XT.
Setting it up is tricky because MusicGen is tightly pinned to old PyTorch versions. You need to manually install most dependencies and then install MusicGen itself with "--no-deps" to avoid overwriting your (ROCm-)PyTorch setup.
MusicGen is part of Meta’s AudioCraft project and generates audio by predicting compressed audio tokens instead of raw waveforms. The generated tracks often sound quite generic, which is a known limitation of current AI music models. Still, it can be useful for quickly prototyping ideas, generating background music, creating sound textures, or experimenting with AI-generated audio.
The results can also be improved by generating continuations of the audio multiple times. By extending the output step by step it is possible to create longer pieces of music of two to three minutes that develop more structure than the short clips shown here.
Video workflow:
- Recorded with OBS
- Edited in Kdenlive
- Transcoded with VAAPI (H.264)
No cloud, real hardware.
Everything runs on Linux, so anyone can set this up.
No GPU? No problem, you can also run it using PyTorch’s CPU backend, just much slower.
#AI #MachineLearning #MusicGen #GenerativeAI #AIaudio #OpenSource #Linux #LocalAI #Fediverse #Tech
Got an idea? Describe it in one sentence via AI 🔍🥼
Start here → https://dot.fm/AISearch
Our Intelligent .FM Domain Search uses AI to translate your concept into a brand-ready domain name built for audio, voice, and streaming.
🎧 Podcasts
🤖 AI voice agents
📡 Streaming platforms
🚀 Audio startups
This isn’t keyword search. It’s semantic signal matching — built for the AI-Audio era. Own a name that sounds like the future.
#dotFM #AIAudio #Branding #DomainNames #FutureOfAudio #AISearch #Artifical
🎙️ Expired .FM domains are now LIVE at auction with Namecheap.
Browse & bid → https://Get.fm/auction
Great brands don’t always start new — sometimes you win them.
Perfect for:
🎧 Podcasts
🤖 AI voice agents
📡 Streaming platforms
🚀 Audio startups
Own the signal. 📡
#dotFM #DomainAuctions #AIAudio #Podcasting #VoiceAI #DomainNames #Domain #DNS
