Jul 22, 03:03 PM

Stability AI Releases Open-Source Text-to-Audio Model Generating 47-Second Audio at 44.1kHz

Stability AI has announced the release of Stable Audio Open, an open-weight text-to-audio model. This model can generate high-quality stereo audio at 44.1kHz from text prompts, with variable lengths up to 47 seconds. The release includes a research paper detailing the architecture and training process, which utilized Creative Commons data. This open-source model is expected to benefit artists and researchers by providing a baseline for new models and enabling fine-tuning. It runs on consumer-grade hardware.

#Stability AI #Stable Audio Open #Creative Commons

Written with ChatGPT (GPT-4o).

Sources

Zhengzhong Tu@_vztu
2 years ago
🚨Stable Audio Open 🌟𝐏𝐫𝐨𝐣: https://t.co/nqnCqtw9x5 🚀𝐀𝐛𝐬: https://t.co/Oy5Kf3UGs3 describe the architecture and training process of a new open-weights text-to-audio model trained with Creative Commons data. https://t.co/PEAJ5oBKS2
Vlad Ruso PhD@vlruso
2 years ago
Stability AI Open-Sources Stable Audio Open: An Audio Generation Model with Variable-Length (up to 47s) Stereo Audio at 44.1kHz from Text Prompts https://t.co/mloTVqDRLx #StabilityAI #AI #GenerativeModels #OpenSource #AudioGeneration #ai #news #llm #ml #research #ainews #inno… https://t.co/QLhHuxBerV
audai@audaiuk
2 years ago
Stable Audio Open: Research Paper - Stability AI https://t.co/roJ6tZJG7R

Additional media

Image #1 for story stability-ai-releases-open-source-text-to-audio-model-generating-47-second-audio

Image #2 for story stability-ai-releases-open-source-text-to-audio-model-generating-47-second-audio

Stability AI Releases Open-Source Text-to-Audio Model Generating 47-Second Audio at 44.1kHz

Sources

Additional media

Similar Stories