Tag: Audio
-
Google NotebookLM now has a feature where it creates a podcast out of sources you place in it
Key points Google NotebookLM has a feature where it creates a podcast out of sources you place in it. Google NotebookLM now has a feature where it creates a podcast out of sources you place in it
-
RunwayML Audio Limitation
Key points RunwayML allows audio input up to 30 seconds in length. RunwayML allows audio input up to 30 seconds in length.
-
Hume AI’s Latest Voice-to-Voice Model EVI-2
Key points Hume AI has launched EVI-2, its latest voice-to-voice model, designed for human-like conversations. Hume AI has launched its latest voice-to-voice model, EVI-2, designed for human-like conversations.
-
Qwen team released a model that can be one of the pieces for Open Source Advanced Audio
Key points The post states that the Qwen team released a model it describes as one possible piece of open source advanced audio, linking to Qwen2-Audio-7B-Instruct on Hugging Face. Qwen team released a model that can be one of the pieces for Open Source Advanced Audio https://huggingface.co/Qwen/Qwen2-Audio-7B-Instruct
-
Black Forest Labs Announces Flux Text-to-Image Model
Key points Black Forest Labs announced the release of Flux, a new text-to-image model. The model is available for testing on their platform, and examples of its capabilities are provided. Black Forest Labs has announced the release of Flux, a new text-to-image model. The model is available for testing on their platform. Examples of its […]
-
Suno AI extends generation from 6 seconds to 60 seconds
Key points Suno AI can now continue generation from sounds from 6 seconds to 60 seconds. Suno AI can now continue generation from sounds from 6 seconds to 60 seconds
-
ElevenLabs Launches iOS App
Key points ElevenLabs launched an iOS app that turns any text into audio narration with AI. ElevenLabs launches iOS app that turns any text into audio narration with AI
-
Stable Radio
Key points Stable Radio is a project that combines images generated by SDXL Turbo with audio generated by Stable Audio. Stable Radio is a project that combines images generated by SDXL Turbo with audio generated by Stable Audio.
-
OpenAI shared a technology called Voice Engine
Key points OpenAI shared a technology called Voice Engine. OpenAI shared a technology called Voice Engine
-
Suno v3 available to general public
Key points Suno v3 is now available to the general public, allowing users to create songs with AI. Two example tracks about ‘Roary’ were shared, demonstrating the platform’s capabilities. Suno v3 is now available to the general public, allowing users to create songs with AI. Two example tracks about ‘Roary’ were shared, demonstrating the platform’s […]