Platform WatchJune 29, 2026via Vercel Blog
Realtime voice, speech, and transcription now supported on AI Gateway
Why it matters
Vercel democratizes voice AI infrastructure by adding realtime voice, speech, and transcription to AI Gateway with cost parity to text models—lowering the barrier for developers to build conversational agents without vendor lock-in or hidden fees.
Key signals
- Realtime voice agents now supported on Vercel AI Gateway
- Speech-to-text and text-to-speech capabilities in beta
- Same observability and spend controls as text/image/video models
- No markup or platform fees for voice models
- Bring-your-own-key support included
- Near real-time audio I/O for conversational agents
- Tool-calling capability mid-conversation for voice agents
- Browser-based playground for no-code testing
- useRealtime hook for WebSocket management and audio capture
The hook
Realtime voice agents just went live on Vercel's AI Gateway. No markup. No platform fees. Same controls as text.
now supports voice and audio models. You can build realtime voice agents, generate speech from text, and transcribe audio to text. This provides the same observability, spend controls, and bring-your-own-key support as text, image, and video models in AI Gateway, with no markup or platform fees. These capabilities are in beta and available via 7.AI GatewayAI SDK
With realtime support, a single model takes audio in and audio out, so a user can talk and hear a reply back in near real time instead of waiting on a chain of separate models.
Two ways to get started:
A voice agent has two pieces: a server route that mints a short-lived token, so your API key never reaches the client, and a browser component that connects with it.
Add the token route:
Then connect from the browser. The hook fetches that route and manages the WebSocket connection, microphone capture, and audio playback:useRealtime
You can also try audio models without writing any code. Open the , click into a , and interact with it right in the browser:models pagemodel
For more information on , , and models on AI Gateway, see the documentation. To view a list of all the supported , , and models on AI Gateway, check the full list .realtime voicespeechtranscriptionrealtime voicespeechtranscriptionhere
Capability
What it does
Realtime voice agents
Model listens to the user, works out a response, and speaks it back in a live, low-latency conversation. It can call your tools mid-conversation to look something up or take an action. The hook handles microphone capture and playback.useRealtime
Text to speech
Generate spoken audio from text, with a selectable voice and output format such as MP3. Use it for voiceovers, audio versions of written content, and spoken responses.
Speech to text
Transcribe recordings into text, from a file buffer, base64 string, or URL. Use it for voice notes or other transcriptions.
Follow the realtime example below or the to add a voice agent to your app.realtime quickstart...