Realtime voice, speech, and transcription now supported on AI Gateway
BetaVerifiedAdded Sep 22, 2026
AI Gateway 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.
Topics: AI agents, Streaming, Observability, Developer tools, Performance
Summaries of vendors' own notes. Product names and logos belong to their owners; logos via logo.dev.
More AI SDK and AI Gateway releases
Every AI SDK and AI Gateway release| Date | Release | Type |
|---|---|---|
| Jun 29 | Sandboxes now expire based on last use Update | Update |
| Jun 29 | xAI Grok audio models now available on Vercel AI Gateway Update | Update |
| Jun 30 | Vercel Agent has updated pricing Pricing | Pricing |
| Jun 30 | Claude Sonnet 5 now available on Vercel AI Gateway Update | Update |
| Jun 30 | An expanded Vercel Agent: chat, investigations, and approved actions, now in public beta Beta | Beta |
| Jun 30 | Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) now on AI Gateway Update | Update |
| Jun 30 | Vercel Sandbox now support Custom Images Beta | Beta |
| Jul 1 | Claude Fable 5 access restored on AI Gateway Update | Update |
