PulseAugur
EN
LIVE 10:24:48

Block unveils Dessa, a speech-only full-duplex AI model

By PulseAugur Editorial · [2 sources] ·

Block's AI research lab has introduced Dessa, a novel full-duplex speech model trained exclusively on human conversation audio. Unlike many current voice agents that rely on text-first architectures, Dessa operates directly from speech input to speech output, enabling it to listen and speak simultaneously. This approach allows for more natural interactions, including mid-sentence interruptions and backchanneling cues, and was trained on a single NVIDIA GB200 NVL72 rack. AI

IMPACT This speech-only training approach could lead to more natural and emotionally nuanced voice agents, potentially impacting the development of future conversational AI.

RANK_REASON Block's AI lab released Dessa, a full-duplex speech model trained only on speech. [lever_c_demoted from frontier_release: ic=2 ai=1.0]

Read on Mastodon — mastodon.social →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

Block unveils Dessa, a speech-only full-duplex AI model

How we ranked this

Signal score
44 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Significant
Block's AI lab released Dessa, a full-duplex speech model trained only on speech. [lever_c_demoted from frontier_release: ic=2 ai=1.0]
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [2]

  1. MarkTechPost TIER_1 English(EN) · Michal Sutter ·

    Block Unveils Dessa, a Full-Duplex Speech Model Trained Only on Speech

    <p>Block’s AI lab released Dessa, a full-duplex speech-to-speech model trained only on human conversation audio. It runs locally on a MacBook Pro M4 Max, but Block has published no size, benchmarks or weights.</p> <p>The post <a href="https://www.marktechpost.com/2026/10/29/block…

  2. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    📰 Block Unveils Dessa, a Full-Duplex Speech Model Trained Only on Speech Block’s AI lab released Dessa, a full-duplex speech-to-speech model trained only on hum

    📰 Block Unveils Dessa, a Full-Duplex Speech Model Trained Only on Speech Block’s AI lab released Dessa, a full-duplex speech-to-speech model trained only on human conversation audio. It runs locally on a MacBook Pro M4 Max, but Block has published no size, benchmarks or... 📰 Sour…

    LINKS marktechpost.com/…/block-dessa-full-duple…

RELATED ENTITIES

RELATED TOPICS