Audio Language Model

Interfaze, a younger YC’s startup, has open-sourced a brand new speech recognition mannequin. It is known as diffusion-gemma-asr-small. The mannequin transcribes audio by way of a diffusion decoder, not an autoregressive one. It is described as the primary multilingual audio diffusion ASR mannequin. One adapter handles six languages. The analysis workforce educated solely about 42M…

Gradium right this moment launched two real-time speech translation fashions: stt-translate and s2s-translate. Both run throughout 5 languages and stream outcomes dwell within the browser. Gradium claims a greater accuracy-latency tradeoff than gpt-realtime-translate and gemini-3.5-live-translate. It additionally provides output voice management, together with cloning, that gpt-realtime-translate lacks. TL;DR Gradium launched two real-time speech translation fashions:…

In this tutorial, we construct a speech recognition and translation workflow utilizing NVIDIA Canary-1B-v2. We start by establishing the required audio, NeMo, NumPy, and SciPy dependencies, then load the Canary mannequin on a GPU-enabled runtime for environment friendly inference. From there, we put together audio right into a clear 16 kHz mono format, carry out…

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…

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…