Skip to content
Modelwire
Subscribe

OpenAI's GPT-Live-1 enables simultaneous speech input and output for developers

Source published ·Modelwire updated

Original coverage: The Decoder ↗·How Modelwire adds context

Illustration accompanying: OpenAI's GPT-Live-1 API lets developers build apps that talk and listen at the same time

The development

OpenAI's GPT-Live-1 API introduces full-duplex speech capabilities to developers, enabling applications where models listen and respond simultaneously without turn-taking delays. The 80.1 percent interactivity score represents a substantial leap from the prior 45.4 percent baseline, signaling meaningful progress toward natural conversational AI. At $0.05 per minute, pricing reflects the computational overhead of concurrent bidirectional processing. This release targets a critical friction point in voice-first applications: latency and conversational naturalness. For developers building customer service, accessibility, and real-time collaboration tools, the capability unlocks new interaction patterns previously constrained by sequential speech models.

Modelwire’s AI-generated summary of coverage from The Decoder.

Modelwire analysis

Skeptical read

Our AI-generated reading of the wider context and the next developments to watch.

The 80.1 percent interactivity score is OpenAI's own metric against OpenAI's own baseline, and the summary offers no detail on how 'interactivity' is actually measured or whether any independent party has reproduced it. That gap matters enormously when the entire commercial case rests on that number.

This is largely disconnected from recent activity in our archive, as we have no prior coverage to anchor it to. It belongs to a broader competitive thread around real-time voice APIs, where Google's Live API (part of the Gemini stack) and Hume AI's empathic voice interface have been staking similar claims about low-latency bidirectional audio. OpenAI is not first here, which makes the framing of this as a capability breakthrough worth scrutinizing rather than accepting.

Watch whether any developer publishes third-party latency benchmarks against Google's Live API within the next 60 days. If independent tests show comparable interactivity scores at lower per-minute cost from a competitor, the $0.05 rate becomes a liability rather than a reasonable overhead premium.

This interpretation is generated from the summary above and available source metadata. Our methodology · Report an error

MentionsOpenAI · GPT-Live-1 · The Decoder

MW

How this coverage is produced

Modelwire uses AI to generate summaries and context from source headlines, snippets, and selected archive coverage. Automated checks do not verify every claim, and items are not routinely reviewed by a person before publication. Zacaria Solis operates the site. Read the linked source for the full evidence and report errors through our corrections process.

Modelwire summarizes, we don’t republish. The Decoder originally reported this story as “OpenAI's GPT-Live-1 API lets developers build apps that talk and listen at the same time”. The full content lives on the-decoder.com. If you’re a publisher and want a different summarization policy for your work, see our takedown page.

OpenAI's GPT-Live-1 enables simultaneous speech input and output for developers · Modelwire