Realtime voice, speech, and transcription now supported on AI Gateway
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.
Read Vercel's release noteshttps://vercel.com/changelog/realtime-voice-speech-and-transcription-now-supported-on-ai-gateway
Summaries of vendors' own notes. Product names and logos belong to their owners; logos via logo.dev.
More AI SDK and AI Gateway releases
xAI Grok audio models now available on Vercel AI Gateway
UpdateAI agentsStreamingObservability
An expanded Vercel Agent: chat, investigations, and approved actions, now in public beta
BetaAI agentsSecurityPricing
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) now on AI Gateway
UpdateLLMsStreamingPricing
Also shipped on Jun 29, 2026
Dynamic Iceberg table replication (General availability)
GAData integrationApache Iceberg
Databricks SQL version 2026.20 is now available in Preview
PreviewSQLGovernanceObservability
Govern LLMs in Unity Catalog with model services (Beta)
BetaLLMsGovernanceObservability