Back to articles
DevPickView feed
PC Watchby 劉 尭
Original published:

No longer feels like talking to AI, 'Dessa' learned only from audio

No longer feels like talking to AI, 'Dessa' learned only from audio
AI summary
Editorial policy

Block announced 'Dessa', a full-duplex voice conversation model trained exclusively on human conversation audio, as a research preview.

Key points

  • •Block announced the full-duplex voice conversation model 'Dessa' on October 23 (US time).
  • •The model was trained only on human conversation audio and can respond in real-time with backchannels.
  • •It was released as a research preview and achieves natural dialogue similar to human-to-human conversation.
Read the original(opens in a new tab)
#LLM / Model Trends#Image / Video / Audio Generation#Dessa#Block

Related articles

See more
ITmedia AI+

Block, led by Jack Dorsey, unveils 'Dessa', a full-duplex voice model trained solely on voice, saying it feels 'like talking to a person'

Block announced a research preview of 'Dessa', a full-duplex voice model trained exclusively on human conversational voice without using text or pre-trained models.

The Verge

Jack Dorsey’s Block made an AI model that talks to you like an awkward new friend

Block announced an AI model named Dessa trained entirely on human conversation data and shared chat logs to demonstrate its capabilities.

TechCrunch

Block’s new voice model sounds eerily human

Block explained that its new voice model is capable of running locally on a MacBook M4 Max.

Hacker News

Dessa: the most authentic full-duplex speech model ever built

An article introduces the research preview of 'Dessa', a full-duplex speech model designed to learn speaking by listening, mimicking human language acquisition.

gihyo.jp

Block、キャラクター化したAIエージェントと作業するデスクトップアプリ「Berd」をオープンソース化(opens in a new tab)

Blockが社内開発のAI搭載デスクトップアプリ「Berd」をオープンソース化。キャラクター化されたAIエージェントとの対話型作業環境を提供する。