Skip to content
01NewAITools.ai

Home/Voice and audio/Dessa

Editorial pickCheck site

Dessa

Block's full-duplex speech-to-speech model, trained from scratch on human conversation. No public access yet.

Block's research lab says Dessa was trained only on human conversation, with no text and no pretrained models. Block says it runs locally on a MacBook Pro M4 Max or better. Early access goes to a small group of AI safety researchers. No weights, release date, or benchmarks have been published.

Visit official siteVoice and audio ranks

Where it ranks

Pricing

Check site

No public access yet. Block has not published a price.

Checked

Added October 26, 2026

Last verified October 26, 2026

Dated releases

  • Block announced Dessa, a full-duplex speech-to-speech model with no public weights or release date.

    Block·TechCrunch

Also in voice and audio

  • ElevenLabs · Text to speech, voice tools, and an API for putting speech in a product.
  • Suno · Makes a full song, vocals included, from a description or your lyrics.
  • Descript · Edit video and podcasts by editing the transcript text.