Computational Model Studio · Model release
GPT-Live 1
Hold full-duplex spoken conversations with simultaneous listening and speech output.
Developer: OpenAI · Last verified:
What it is designed to do
Hold full-duplex spoken conversations with simultaneous listening and speech output.
- Primary contribution
- generation transformation
- Input
- text, audio
- Output
- text, audio (streaming spoken response, text response)
Documented uses: Hold full-duplex spoken conversations with simultaneous listening and speech output.
Access and deployment
- GPT-Live 1 OpenAI API — available. Provider account and access under current service rules. Offering documentation Complete provider service terms were not reviewed for this offering.
- provider hosted: Use exact model ID gpt-live-1 through a supported provider endpoint. Limits: No local hardware or weight-download claim follows from this API offering..
Technical profile and review notes
- Construction
- learned
- Representation
- neural
- Normalized architecture tags
- No normalized architecture tag assigned
- Lifecycle
- active
Inclusion rationale: The full-duplex Live model is a documented speech-in/speech-out system rather than mere transcription or text-to-speech.
Limitations
- The publisher’s described output is recorded as the exact media form shown; surrounding editing tools or orchestration are not attributed to this model.
- Hosted API access does not establish downloadable weights or local hardware feasibility.
Sources and related Studio records
Sources
Connections
- In areaComputational Models
- Supports functionConverse in audio
- OfferingGPT-Live 1 OpenAI API