Block’s new voice model sounds eerily human
- ID
- 39086
- Status
- summarized
- Published
- 25 Oct 2026, 12:00 AM
- Fetched
- 25 Oct 2026, 12:36 AM
- Provider
- TechCrunch
- Category
- technology
- Original URL
- https://techcrunch.com/2026/10/24/blocks-new-voice-model-sounds-eerily-human/
- Source URL
- https://techcrunch.com/feed/
Summary
- Score
- 6.0
- Created
- 25 Oct 2026, 12:36 AM
- Tags
- Audience
- ai_ml_learnersdevelopersai_agent_users
What happened
Block's research lab released a voice model called Dessa, announced by Jack Dorsey on October 23, 2026, which the company says runs locally and was trained entirely on human speech using a single NVIDIA GPU. Dessa is full-duplex — it listens and speaks at the same time — matching the approach of OpenAI's GPT-Live, and Block claims emotion is baked into the model rather than driven by voice tags like ElevenLabs v4 or Fish Audio Drama 3. Block also says Dessa's knowledge comes only from its conversational training data, not from a paired LLM, and the article gives no benchmarks, latency numbers, license, weights availability, or release date.
Why it matters
The interesting claim is architectural: no ASR-to-text-to-TTS pipeline, so prosody and pauses survive instead of being flattened into text. But nothing here tells you whether you can actually use it — no weights, license, latency, or hardware specs beyond 'a single NVIDIA GPU'. Until those exist, treat Dessa as a demo to watch, not a component to plan around; if you're building voice agents today, your decision is still between tag-driven TTS and full-duplex APIs that ship with real docs.
Discussion angle
If Dessa really has no text stage and no paired LLM, what happens when a user asks it something outside its conversational training data — is dropping the text pipeline a genuine quality win or a capability trade-off?