AI Gateway now supports streaming transcription
- Source
- vercel.com
- Author
- Kevin Dawkins
- Date
Context
Vercel's streaming transcription support lets an application send audio as it is captured and receive text as recognition progresses. That removes the requirement to wait for a complete recording before obtaining a transcript. An existing text-based can consume those updates as its input, giving it a path to accept speech without changing its underlying text interface. The July 22 launch described the feature as beta and required a -capable transcription model. Generating a spoken reply is a separate step, using speech generation or a two-way voice system.
- streaming — Sending a model's response token by token as it is generated, so the reader sees text immediately instead of waiting for the whole answer.
- AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
“Previously, transcription required a complete audio file and returned the full transcript in a single response.”
“The agent itself does not change: it still receives text, so this works with any text-based agent.”
“For agents that speak back, pair it with speech generation, or use realtime voice for full two-way conversation.”
Checking sign-in…
Loading comments…