Not established from the available sources.
OPENAI · MODEL RELEASE TRACKER
OpenAI GPT-Live-1
OpenAI GPT-Live-1 is reported as a voice/speech model released earlier in 2026. Media coverage describes it as a full‑duplex voice model that can talk and listen at the same time.CURRENT SNAPSHOT1/5 DIMENSIONS WITH DATA
The dimensions that change the decision.
Not established from the available sources.
Modality: voice / speechReferred to as a voice model and shown in an example voice conversation (article references a conversation between OpenAI's GPT-Live-1 voice model and Dessa).
Not established from the available sources.
Not established from the available sources.
VERIFIABLE FACTS
Every value stays attached to a source and date.
MODALITIES · Modality: voice / speechDEVELOPER CLAIM
Referred to as a voice model and shown in an example voice conversation (article references a conversation between OpenAI's GPT-Live-1 voice model and Dessa).
RELEASE · Release timingDEVELOPER CLAIM
Reportedly released earlier in 2026 (article states Block's Dessa is 'just like the GPT-Live model OpenAI released earlier this year').
CAPABILITIES · Full‑duplex capabilityDEVELOPER CLAIM
Described as a full‑duplex model that can talk and listen at the same time (per article comparing Dessa to GPT-Live).
WHAT CHANGED
Stored passport versions, without reconstructed history.
CAPABILITIES · Full‑duplex capability+ Described as a full‑duplex model that can talk and listen at the same time (per article comparing Dessa to GPT-Live).
RELEASE · Release timing+ Reportedly released earlier in 2026 (article states Block's Dessa is 'just like the GPT-Live model OpenAI released earlier this year').
MODALITIES · Modality− Described as a voice (speech) model that takes part in spoken conversations.
MODALITIES · Modality: voice / speech+ Referred to as a voice model and shown in an example voice conversation (article references a conversation between OpenAI's GPT-Live-1 voice model and Dessa).