Build realtime voice agents on AI Gateway
Not a pilot. Vercel just unified voice, text, and video through a single API Gateway—same auth, same observability, same spend controls.
Why it matters
Vercel's AI Gateway now supports realtime voice agents alongside text/image/video, lowering the friction for developers to build multimodal AI applications with unified routing, observability, and cost controls across all modalities.
The key facts
7 to knowAudio/voice support added to Vercel AI Gateway
Supports realtime voice, text-to-speech, and speech-to-text via single API calls
Models from OpenAI and xAI available
Features: server-side voice activity detection (VAD), barge-in interruption, mid-conversation tool calls
Available in AI SDK 7 (beta)
Browser integration via useRealtime hook with WebSocket authentication
Single API key for text, image, video, and audio routing with unified provider support, observability, and spend controls
Go to the source
Vercel Blogvercel.com
Publisher excerpt: now supports audio/voice. You can add realtime voice, text to speech, and speech to text with the same calls you already use for text, image, and video, routed through AI Gateway alongside every other modality.AI Gateway Audio launches with models from and . Each call gets the same provider…