cd /news/artificial-intelligence/blocks-dessa-the-speech-ai-that-neve… · home › topics › artificial-intelligence › article
[ARTICLE · art-156700] src=byteiota.com ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

Block’s Dessa: The Speech AI That Never Touched Text

Block has introduced Dessa, a full-duplex speech model trained solely on human audio with no text data and no pretrained weights, according to byteiota. The model is positioned for developers building voice applications.

read1 min views1 publishedOct 24, 2026

Block's Dessa is a full-duplex speech model trained solely on human audio — no text, no pretrained weights. Here's what it means for developers building voice applications.

The post Block’s Dessa: The Speech AI That Never Touched Text appeared first on byteiota .

source & further reading
byteiota.com — original article OpenAI Models and Codex Are Now on Google Cloud OpenAI 12-Hour Prompt Cache Is Live: What Agent Developers Must Do Now JFrog AI-SEC Detects Shadow AI on Developer Workstations
── more in #artificial-intelligence 4 stories · sorted by recency
── more on @block 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/blocks-dessa-the-spe…] indexed:0 read:1min 2026-10-24 · —