TTS

Auto Added by WPeMatico

Meet ‘Kani-TTS-2’: A 400M Param Open Source Text-to-Speech Model that Runs in 3GB VRAM with Voice Cloning Support

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

The landscape of generative audio is shifting toward efficiency. A new open-source contender, Kani-TTS-2, has been released by the team at nineninesix.ai. This model marks a departure from heavy, compute-expensive TTS systems. Instead, it treats audio as a language, delivering high-fidelity speech synthesis with a remarkably small footprint. Kani-TTS-2 offers a lean, high-performance alternative to […]

Meet ‘Kani-TTS-2’: A 400M Param Open Source Text-to-Speech Model that Runs in 3GB VRAM with Voice Cloning Support Read More »

What Is Sociophonetics and Why It Matters for AI

ai, AI (Artificial Intelligence), ai training data, Artificial Intelligence, Audio Collection, Conversational AI, Data Collection, Machine Learning, Shaip Blogs, Speech Recognition, TTS

You’ve probably had this experience: a voice assistant understands your friend perfectly, but struggles with your accent, or with your parents’ way of speaking. Same language. Same request. Very different results. That gap is exactly where sociophonetics lives — and why it suddenly matters so much for AI. Sociophonetics looks at how social factors and

What Is Sociophonetics and Why It Matters for AI Read More »

Mistral AI Launches Voxtral Transcribe 2: Pairing Batch Diarization And Open Realtime ASR For Multilingual Production Workloads At Scale

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

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

Mistral AI Launches Voxtral Transcribe 2: Pairing Batch Diarization And Open Realtime ASR For Multilingual Production Workloads At Scale Read More »

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 »

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 »

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 »

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 »

Google AI Releases TranslateGemma: A New Family of Open Translation Models Built on Gemma 3 with Support for 55 Languages

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

Google AI has released TranslateGemma, a suite of open machine translation models built on Gemma 3 and targeted at 55 languages. The family comes in 4B, 12B and 27B parameter sizes. It is designed to run across devices from mobile and edge hardware to laptops and a single H100 GPU or TPU instance in the

Google AI Releases TranslateGemma: A New Family of Open Translation Models Built on Gemma 3 with Support for 55 Languages Read More »

What Is Sociophonetics and Why It Matters for AI

ai training data, Artificial Intelligence, Audio Collection, Conversational AI, Data Collection, Machine Learning, Shaip Blogs, Speech Recognition, TTS

You’ve probably had this experience: a voice assistant understands your friend perfectly, but struggles with your accent, or with your parents’ way of speaking. Same language. Same request. Very different results. That gap is exactly where sociophonetics lives — and why it suddenly matters so much for AI. Sociophonetics looks at how social factors and

What Is Sociophonetics and Why It Matters for AI Read More »

Microsoft AI Releases VibeVoice-Realtime: A Lightweight Real‑Time Text-to-Speech Model Supporting Streaming Text Input and Robust Long-Form Speech Generation

Artificial Intelligence, Editors Pick, New Releases, Staff, Technology, TTS, Voice AI

Microsoft has released VibeVoice-Realtime-0.5B, a real time text to speech model that works with streaming text input and long form speech output, aimed at agent style applications and live data narration. The model can start producing audible speech in about 300 ms, which is critical when a language model is still generating the rest of

Microsoft AI Releases VibeVoice-Realtime: A Lightweight Real‑Time Text-to-Speech Model Supporting Streaming Text Input and Robust Long-Form Speech Generation Read More »