k
keynews.ai
keynews.ai
FrontierThe story, in brief

Miso Labs Releases MisoTTS: An 8B Emotive Text-to-Speech Model with Open Weights

Open weights just got emotional. Miso Labs drops 8B TTS model that conditions on speaker tone—no parameter bloat required.

Reporting by MarkTechPost 1 min brief
Illustration of a transparent lens revealing connected networks across layers of paper.
Exploring the next frontier of AI research.AI illustration by KeyNews
The KeyNews take

Why it matters

Miso Labs demonstrates a novel approach to scaling multimodal capabilities (text-to-speech with emotional conditioning) using residual vector quantization rather than parameter explosion. This matters for founders building speech applications: smaller models with better conditioning = lower inference costs and faster deployment.

The key facts

5 to know

  1. Model size: 8B parameters (7.7B backbone + 300M depth decoder)

  2. Architecture: Uses residual vector quantization (RVQ) for sonic scaling without parameter scaling

  3. Conditioning: Responds to both text AND audio context (speaker tone awareness)

  4. License: Open weights (community access)

  5. Multimodal capability: Text-to-speech with emotional/contextual awareness

Go to the source

MarkTechPostmarktechpost.com

Publisher excerpt: Miso Labs has released MisoTTS, an open-weights 8B text-to-speech model. It uses residual vector quantization (RVQ) to scale its sonic range without scaling parameters, and conditions on both text and audio context to respond to speaker tone. The architecture pairs a 7.7B backbone with a 300M depth…
Read original report
Back to today's editionMore frontier news

The wider picture

View all
Illustration of a transparent lens revealing connected networks across layers of paper.
AI illustration by KeyNews
Frontier01

Alibaba Unveils Zhenwu V900 — and Plans Qwen Models With Up to 10 Trillion Parameters

Alibaba is advancing on two fronts simultaneously: announcing a custom AI accelerator (Zhenwu V900) and committing to massive model scale (10T parameters for future Qwen releases). For practitioners, this matters as a credible third-party capability play outside the US-China licensing squeeze; for enthusiasts, it's a significant lab-race signal about training compute and parameter scaling as competitive levers.

TechRepublic
Illustration of a transparent lens revealing connected networks across layers of paper.
AI illustration by KeyNews
Frontier02

Kyutai Releases Voice of Reason: A Speech-Native Model that Solves Spoken Math with Reinforcement Learning

A new capability frontier: models that reason directly in speech without transcription bottlenecks. This changes how we think about multimodal reasoning and what's possible with open-weight releases at scale.

MarkTechPost
Illustration of a transparent lens revealing connected networks across layers of paper.
AI illustration by KeyNews
Frontier03

Claude Opus 5.5, GPT-6 Sol, GPT-6 Luna, and a new price war

Frontier labs are shipping upgraded reasoning and multimodal models in rapid succession, signaling acceleration in the capability race. Simultaneous price cuts reshape AI economics for practitioners.

Simon Willison