Stability AI has launched open weights for Stable Audio 3 together with a technical research paper. Stable Audio 3 is a household of latent diffusion fashions that generate stereo audio at 44.1 okHz. The fashions help variable-length outputs, inpainting-based enhancing, and quick inference. What Is Stable Audio 3? Stable Audio 3 is a household of…
StepFun, the Shanghai-based AI lab, launched StepAudio 2.5 Realtime. It is an end-to-end real-time speech massive language mannequin with absolutely customizable persona capabilities. StepAudio 2.5 Realtime is a voice mannequin that operates in actual time. Unlike pipeline-based methods that separate speech recognition, reasoning, and synthesis into sequential steps, that is an end-to-end mannequin. Audio goes…
Voice AI has a grimy secret: most of it was by no means designed for dialog. The dominant paradigm — feed textual content in, get audio out — traces its lineage to audiobook narration and voiceover manufacturing, the place the mannequin by no means hears the particular person on the opposite finish. That’s high-quality while…
IBM launched two new open speech recognition fashions— Granite Speech 4.1 2B and Granite Speech 4.1 2B-NAR — and they make a compelling case for what a ~2B-parameter speech mannequin can do. Both can be found on Hugging Face below the Apache 2.0 license. The pair targets a particular drawback that enterprise AI groups know…
Understanding what’s occurring in an audio clip is a deceptively exhausting drawback. Transcribing spoken phrases is the straightforward half. A really succesful system additionally wants to acknowledge who’s talking, detect their emotional state, interpret background sounds, analyze musical content material, and reply time-grounded questions like ‘what did the speaker say on the 2-minute mark?’. Tackling…
Automatic speech recognition (ASR) is becoming a core building block for AI products, from meeting tools to voice agents. Mistral’s new Voxtral Transcribe 2 family targets this space with 2 models that split cleanly into batch and realtime use cases, while keeping cost, latency, and deployment constraints in focus. The release includes: Voxtral Mini Transcribe…
Inworld AI has introduced Inworld TTS-1.5, an upgrade to its TTS-1 family that targets realtime voice agents with strict constraints on latency, quality, and cost. TTS-1.5 is described as the number top ranked text to speech system on Artificial Analysis and is designed to be more expressive and more stable than prior generations while remaining…
Meta researchers have introduced Perception Encoder Audiovisual, PEAV, as a new family of encoders for joint audio and video understanding. The model learns aligned audio, video, and text representations in a single embedding space using large scale contrastive training on about 100M audio video pairs with text captions. From Perception Encoder to PEAV Perception Encoder,…
Why do present audio AI fashions usually carry out worse after they generate longer reasoning as a substitute of grounding their selections within the precise sound. StepEnjoyable analysis group releases Step-Audio-R1, a brand new audio LLM designed for check time compute scaling, tackle this failure mode by displaying that the accuracy drop with chain of…
How do you construct a single speech recognition system that may perceive 1,000’s of languages together with many who by no means had working ASR (computerized speech recognition) fashions earlier than? Meta AI has launched Omnilingual ASR, an open supply speech recognition suite that scales to greater than 1,600 languages and could be prolonged to…