Explore
Everything AION read, in seven sections. Pick one, a topic or a time window.
Introducing Clef-omni with full multimodality, plus a faster Clef and a cheaper Clef-flash
Today, we’re releasing Clef-omni, which takes in audio and video input alongside text and image.
mistralai/Voxtral-Mini-4B-Realtime-Arabic
mistralai published the model Voxtral-Mini-4B-Realtime-Arabic on Hugging Face.
A new feature for my blog, built using my voice
I used the ChatGPT desktop app for this, in the Codex tab, using the voice conversation mode, running against a local development environment.
pydantic/pydantic-ai v2.55.0: v2.55.0 (2026-10-09)
<!-- Release notes generated using configuration in .github/release.yml at main -->
VideoCan Your Agent Hear You Now? Building Live Voice Agents with Gemini — Thor Schaeff
An agent that hears you, sees you, and answers in your language, in real time.
These execs think voice AI hasn’t reached its ChatGPT moment yet
Voice AI's often misses important points for its context layer, and causes the whole pipeline to break
Introducing Falcon ASR
We’re introducing Falcon-ASR, our 1.6 billion parameter speech recognition model for Arabic, with a particular focus on the Emirati dialect.
open-webui/open-webui v0.12.0
Approvals and questions from tools still have to be answered in the chat, calls need the Allow Call permission and end after an hour, models can set their own Realtime Voice in the model editor, and the settings can also be given with the "AUDIOREALTIMEENABLED", "AUDIOREALTIMEOPENAIAPIBASEURL", "AUDIOREALTIMEOPENAIAPIKEY", "AUDIOREALTIMEMODEL", "AUDIOREALTIMEVOICE", "AUDIOREALTIMETRANSCRIPTIONMODEL" and "REALTIMECALLPROMPTTEMPLATE" environment variables.
Dual- versus Single-Suggestion AI Support for Radiographic Interpretation in Residents: Randomized Multireader Study
Purpose: To compare dual- and single-suggestion AI support for radiographic interpretation by residents, particularly when the shared AI suggestion was incorrect.
Claude Dashboards & Motion
Ask Claude for live dashboards and animated explainers
Build a voice travel concierge with Amazon Bedrock AgentCore, Managed Knowledge Base and Nova Sonic
Airlines already have apps and websites where travelers check flights, pick seats, and manage bookings, and adding a natural voice layer opens those tasks to spoken requests.
canberkkkkkk/ema-lightning
canberkkkkkk published the model ema-lightning on Hugging Face.
Open-source Mac app that runs EmbeddingGemma 2 locally to search your files by what’s in them
DigUp is a free Mac app that runs Google DeepMind’s new EmbeddingGemma 2 locally over your own files.
SheetSage2: Coherent Lead-Sheet Transcription with Synthetic Supervision
We present SheetSage2, a unified music transcription framework that combines synthetic data, task-specific structured decoding, and autoregressive distillation.
huggingface/transformers v5.18.0: Release 5.18.0
Nemotron 3 Diarization is an open-weight streaming speaker diarization model designed to determine "who spoke when" in real-world audio.
unslothai/unsloth v0.1.903-beta: New Browser + Voice Cloning
This release adds a browser inside Unsloth (browser use coming very soon), so files, web pages and pages the model writes open right beside your chat.
Fine-Tuning NVIDIA Nemotron for Saudi Arabic Dialects, with a Path to Other Languages
Automatic speech recognition must handle how people actually speak, not only the languages and styles that dominate pretraining data.
huggingface/peft v0.21.2
This is a PEFT release fixes an issue that prevented encoder-decoder models to work when using Transformers ≥ 5.18.0.
Gemini 3.8 text-to-speech says hello
Today, we’re introducing two new text-to-speech models to the Gemini family, transforming voice generation from static presets into a dynamic creative studio.
VideoHow a Voice Agent Learns the Rhythm of Conversation — Shawn Wen
Tsung-Hsien (Shawn) Wen, CTO of PolyAI, tells Tim Scarfe why voice agents are harder than text agents.
Willow taps CoreWeave to simplify AI model training
Willow Care Inc., the company behind AI dictation app Willow Voice, chose CoreWeave Inc. for its forward-deployed support rather than compute alone.
StayLameBro/backburner: Your iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cable
Your iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cable Language: Python.
Language Discrimination Improves Linguistic Learning in Multilingual Speech Models
We show that strengthening the model’s ability to discriminate languages during pretraining reduces and, on some measures, closes this multilingual gap on continuous phonetic and higher-level linguistic measures, while preserving substantial cross-language sharing.
mistralai/LIDstral-Arabic
mistralai published the model LIDstral-Arabic on Hugging Face.
Temporal transformer CAN encoder with federated lightweight heads for anomaly detection
Motivated by this gap, we present a privacy-preserving framework for anomaly detection in in-vehicle networks, based on a Temporal Transformer CAN Encoder with Federated Lightweight Heads, to better capture these irregularities.
BanglaRhet: Benchmarking Classical and Transformer Models for Rhetorical and Persuasion Detection in Bangla Political Speech
While Bangla natural language processing has made progress in sentiment analysis and opinion mining, systematic benchmarking of transformer models for fine-grained rhetorical and persuasion technique detection in Bangla political speech remains largely underexplored.
Cactus-Compute/whistle
Cactus-Compute published the model whistle on Hugging Face.
Itgan at NADI 2026 shared task: Parameter-Efficient Whisper Adaptation for Robust, Mixed-Dialect and Code-Switched Arabic ASR
We describe the Itgan systems for the three ASR subtasks of NADI 2026, namely robust country-level ASR (1.1), mixed-dialect ASR (1.2), and Tunisian code-switched ASR (1.3).
No Distillation Needed: Single-Pass Real-Time Talking Heads via Acausal Noise Shaping
Audio-driven facial animation underpins real-time avatars, telepresence, and embodied virtual agents.
SNR-Gated LSTM-Conditioned Diffusion Model for MIMO Channel Estimation
Accurate and low latency channel estimation is critical for modern MIMO systems, particularly under mobility, where channels exhibit structured sparsity and strong temporal correlation.
MiniVer-V: Identifying Minimal Sufficient Evidence for Short Video Verification
We introduce MiniVer-V, a benchmark of 195 short videos with three-way verdict annotations (supported, refuted, insufficient) and 5,510 multimodal evidence units spanning visual keyframes, speech transcripts, and web-retrieved external sources.
Detecting a Shift Is Not Enough: Exact Minimax Limits of Linear Representation Repair
We cast its removal as a statistical decision problem: from noisy differences between paired calibration measurements in $\mathbb{R}^d$, learn one linear map, applied to both sources under a hard distortion budget, that leaves as little of the shift as possible on fresh data.
Conversational Voice Aesthetic Model with Reinforcement Learning from Human Listeners
We introduce Conversational Voice Aesthetic Model, a speech large language model for describing the voice aesthetics of real or synthetic speech responses in natural conversational contexts.
Nobody Truly Agrees on Sentiment: Humans, Bespoke Tools, and LLMs Struggle with Social Media Texts
In this study, we evaluate the inter-rater reliability of three bespoke sentiment analysis tools (TextBlob, VADER, and Twitter-roBERTa-base) and three large language models (LLMs: Qwen3-32B, GPT-OSS-120B, Llama-4-Maverick-17B) against six human raters across 100 tweets.
Beyond Anonymous Captions: Grounding Character Identity in Video Captioning and Question Answering
We present a framework for identity-aware video captioning and person-centric question answering that combines automatic character identification, explicit spatial grounding, and task-specific adaptation.
Disentangling Linguistic and Paralinguistic Information with Routed Sparse Autoencoders
Self-supervised speech encoders contain linguistic and paralinguistic information in a shared, entangled representation space.
SP-DocReader: Difference-Aware Self-Play for Precise Document OCR
We present SP-DocReader, a self-play framework for optical character recognition (OCR) that targets residual errors after supervised fine-tuning.
MemoCare: An Interactive Multimodal Mobile System for Automated Cognitive Screening
MemoCare is an interactive mobile system for automated multimodal cognitive screening.
Steerspeech: Activation Steering For Emotion Control In Generated Speech
We present SteerSpeech, a lightweight activation-steering framework that controls emotion by injecting steering vectors into hidden activations.
Softmax Attention on Gaussian Mixtures: Linear When It Can, Selective When It Must
This work studies the infinite-prompt limit of softmax attention on Gaussian mixtures, which retain the tractability of Gaussian data while introducing latent structure, multimodality, and nonlinear dependencies.
The Labeling Problem in Hallucination Detection Benchmarks: An Empirical Evaluation
In recent years, several methods for detecting when large language models (LLMs) hallucinate have been developed.
Cylindrical Geodesic Flow Matching for Quasiperiodic Physiological Signal Transformation
We introduce cylindrical geodesic flow matching for paired cardiovascular waveform translation.
Sensor Geometry as a Flow-Matching Prior for Multi-Channel Brain Signals
Flow-matching models start from an isotropic Gaussian source, the standard choice when the correlation structure of the data is unknown in advance.
Beyond Speech Captions: Speech-Rewarded Style Planning for Conversational Text-to-Speech
Natural-language style descriptions provide an interpretable interface between large language models (LLMs) and controllable text-to-speech (TTS).
EgoVoice: Proactive Spoken Assistance from Egocentric Multimodal Streams
We introduce EgoVoice, a framework for training and evaluating proactive egocentric spoken assistants.
HINTT Submission to the 2nd MLC-SLM Challenge: Comparing Cascaded and Unified Approaches to Diarization and ASR
This paper presents the HINTT system submitted to the 2nd Challenge and Workshop on Multilingual Conversational Speech Language Model (MLC-SLM).
DuplexAgent-RSI: Recursive Harness Improvement for Full-Duplex Voice Agent Collaboration
Voice agents are converging on a collaboration pattern: a full-duplex interaction model stays on the live channel as the entry to the conversation, while search, reasoning, and coding are handled through asynchronous delegation.
Beyond Report Imitation: Clinically Aware Multi-Image Ultrasound Report Generation from Visible Evidence
We propose CAMEO, a Clinically Aware Multi-image Evidence-grounded Orchestration framework for ultrasound report generation.