Language Model

Auto Added by WPeMatico

Qwen Researchers Release Qwen3-TTS: an Open Multilingual TTS Suite with Real-Time Latency and Fine-Grained Voice Control

ai, AI (Artificial Intelligence), AI Shorts, Applications, Artificial Intelligence, Audio Language Model, Editors Pick, Language Model, Large Language Model, New Releases, Sound, Staff, Tech News, Technology, TTS, Voice AI

Alibaba Cloud’s Qwen team has open-sourced Qwen3-TTS, a family of multilingual text-to-speech models that target three core tasks in one stack, voice clone, voice design, and high quality speech generation. https://arxiv.org/pdf/2601.15621v1 Model family and capabilities Qwen3-TTS uses a 12Hz speech tokenizer and 2 language model sizes, 0.6B and 1.7B, packaged into 3 main tasks. The […]

Qwen Researchers Release Qwen3-TTS: an Open Multilingual TTS Suite with Real-Time Latency and Fine-Grained Voice Control Read More »

Microsoft Releases VibeVoice-ASR: A Unified Speech-to-Text Model Designed to Handle 60-Minute Long-Form Audio in a Single Pass

agentic ai, ai, AI (Artificial Intelligence), AI Agents, Artificial Intelligence, Audio Language Model, Editors Pick, Language Model, New Releases, Sound, Staff, Technology, Voice AI

Microsoft has released VibeVoice-ASR as part of the VibeVoice family of open source frontier voice AI models. VibeVoice-ASR is described as a unified speech-to-text model that can handle 60-minute long-form audio in a single pass and output structured transcriptions that encode Who, When, and What, with support for Customized Hotwords. VibeVoice sits in a single

Microsoft Releases VibeVoice-ASR: A Unified Speech-to-Text Model Designed to Handle 60-Minute Long-Form Audio in a Single Pass Read More »

FlashLabs Researchers Release Chroma 1.0: A 4B Real Time Speech Dialogue Model With Personalized Voice Cloning

agentic ai, ai, AI (Artificial Intelligence), AI Agents, AI Paper Summary, AI Shorts, Applications, Artificial Intelligence, Audio Language Model, Editors Pick, Language Model, Large Language Model, Machine Learning, New Releases, Open Source, Software engineering, Sound, Staff, Tech News, Technology

Chroma 1.0 is a real time speech to speech dialogue model that takes audio as input and returns audio as output while preserving the speaker identity across multi turn conversations. It is presented as the first open source end to end spoken dialogue system that combines low latency interaction with high fidelity personalized voice cloning

FlashLabs Researchers Release Chroma 1.0: A 4B Real Time Speech Dialogue Model With Personalized Voice Cloning Read More »

Inworld AI Releases TTS-1.5 For Realtime, Production Grade Voice Agents

ai, AI (Artificial Intelligence), Artificial Intelligence, Audio Language Model, Editors Pick, Language Model, New Releases, Sound, Staff, Technology, TTS

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

Inworld AI Releases TTS-1.5 For Realtime, Production Grade Voice Agents Read More »

Liquid AI Releases LFM2.5-1.2B-Thinking: a 1.2B Parameter Reasoning Model That Fits Under 1 GB On-Device

ai, AI (Artificial Intelligence), AI Shorts, Applications, Artificial Intelligence, Editors Pick, Language Model, Machine Learning, New Releases, Python, Staff, Tech News, Technology, Uncategorized

Liquid AI has released LFM2.5-1.2B-Thinking, a 1.2 billion parameter reasoning model that runs fully on device and fits in about 900 MB on a modern phone. What needed a data center 2 years ago can now run offline on consumer hardware, with a focus on structured reasoning traces, tool use, and math, rather than general

Liquid AI Releases LFM2.5-1.2B-Thinking: a 1.2B Parameter Reasoning Model That Fits Under 1 GB On-Device Read More »

Zhipu AI Releases GLM-4.7-Flash: A 30B-A3B MoE Model for Efficient Local Coding and Agents

agentic ai, ai, AI (Artificial Intelligence), AI Agents, AI Shorts, Applications, Artificial Intelligence, Editors Pick, Language Model, New Releases, Staff, Tech News, Technology

GLM-4.7-Flash is a new member of the GLM 4.7 family and targets developers who want strong coding and reasoning performance in a model that is practical to run locally. Zhipu AI (Z.ai) describes GLM-4.7-Flash as a 30B-A3B MoE model and presents it as the strongest model in the 30B class, designed for lightweight deployment where

Zhipu AI Releases GLM-4.7-Flash: A 30B-A3B MoE Model for Efficient Local Coding and Agents Read More »

How to Design a Fully Streaming Voice Agent with End-to-End Latency Budgets, Incremental ASR, LLM Streaming, and Real-Time TTS

agentic ai, ai, AI (Artificial Intelligence), Artificial Intelligence, Audio Language Model, Editors Pick, Language Model, Sound, Staff, Technology, TTS, Tutorials

In this tutorial, we build an end-to-end streaming voice agent that mirrors how modern low-latency conversational systems operate in real time. We simulate the complete pipeline, from chunked audio input and streaming speech recognition to incremental language model reasoning and streamed text-to-speech output, while explicitly tracking latency at every stage. By working with strict latency

How to Design a Fully Streaming Voice Agent with End-to-End Latency Budgets, Incremental ASR, LLM Streaming, and Real-Time TTS Read More »

Microsoft Research Releases OptiMind: A 20B Parameter Model that Turns Natural Language into Solver Ready Optimization Models

ai, AI (Artificial Intelligence), AI Paper Summary, AI Shorts, Applications, Artificial Intelligence, Editors Pick, Language Model, Large Language Model, Machine Learning, New Releases, Open Source, Staff, Tech News, Technology

Microsoft Research has released OptiMind, an AI based system that converts natural language descriptions of complex decision problems into mathematical formulations that optimization solvers can execute. It targets a long standing bottleneck in operations research, where translating business intent into mixed integer linear programs usually needs expert modelers and days of work. What OptiMind Is

Microsoft Research Releases OptiMind: A 20B Parameter Model that Turns Natural Language into Solver Ready Optimization Models Read More »

Nous Research Releases NousCoder-14B: A Competitive Olympiad Programming Model Post-Trained on Qwen3-14B via Reinforcement Learning

agentic ai, ai, AI (Artificial Intelligence), Artificial Intelligence, Editors Pick, Language Model, Large Language Model, New Releases, Open Source, Staff, Technology

Nous Research has introduced NousCoder-14B, a competitive olympiad programming model that is post trained on Qwen3-14B using reinforcement learning (RL) with verifiable rewards. On the LiveCodeBench v6 benchmark, which covers problems from 08/01/2024 to 05/01/2025, the model reaches a Pass@1 accuracy of 67.87 percent. This is 7.08 percentage points higher than the Qwen3-14B baseline of

Nous Research Releases NousCoder-14B: A Competitive Olympiad Programming Model Post-Trained on Qwen3-14B via Reinforcement Learning Read More »

NVIDIA Releases PersonaPlex-7B-v1: A Real-Time Speech-to-Speech Model Designed for Natural and Full-Duplex Conversations

agentic ai, ai, AI (Artificial Intelligence), AI Shorts, Applications, Artificial Intelligence, Audio Language Model, Editors Pick, Language Model, Large Language Model, New Releases, Open Source, Sound, Staff, Tech News, Technology, TTS

NVIDIA Researchers released PersonaPlex-7B-v1, a full duplex speech to speech conversational model that targets natural voice interactions with precise persona control. From ASR→LLM→TTS to a single full duplex model Conventional voice assistants usually run a cascade. Automatic Speech Recognition (ASR) converts speech to text, a language model generates a text answer, and Text to Speech

NVIDIA Releases PersonaPlex-7B-v1: A Real-Time Speech-to-Speech Model Designed for Natural and Full-Duplex Conversations Read More »