{"slug": "ai-gateway-now-supports-streaming-transcription", "title": "AI Gateway now supports streaming transcription", "summary": "Vercel's AI Gateway now supports streaming transcription in beta, allowing users to stream audio in real-time and receive transcript updates as the model produces them, reducing latency for live captioning and voice input. The feature is available through the AI SDK's streamTranscribe function with any streaming-capable transcription model, including OpenAI's gpt-realtime-whisper and xAI's grok-stt.", "body_md": "AI Gateway now supports [streaming transcription](https://vercel.com/ai-gateway/models?modality=audio:transcription&features=websockets). Previously, transcription required a complete audio file and returned the full transcript in a single response. Now you can stream audio in as it's captured and get transcript updates back as the model produces them, keeping latency low for uses like live captioning and voice input.\n\nStreaming transcription is in beta and available through the [AI SDK](https://ai-sdk.dev/docs/ai-sdk-core/transcription#streaming-transcription)'s `streamTranscribe`\n\nfunction with any streaming-capable transcription model.\n\nThe example below streams raw PCM audio to `openai/gpt-realtime-whisper`\n\nand prints each transcript delta as it arrives. The result stream also carries partial and final transcripts:\n\nThe same code works across providers: swap the model string to use `xai/grok-stt`\n\nor any other [streaming-capable transcription model](https://vercel.com/ai-gateway/models?modality=audio:transcription&features=websockets).\n\nStreaming transcription also makes it easy to add a voice mode to an agent. Stream the user's speech to a transcription model and pass the live text to your agent. 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.\n\nFor more information on streaming transcription on AI Gateway, see the [documentation](https://vercel.com/docs/ai-gateway/modalities/speech-to-text#streaming-transcription).", "url": "https://wpnews.pro/news/ai-gateway-now-supports-streaming-transcription", "canonical_source": "https://vercel.com/changelog/ai-gateway-now-supports-streaming-transcription", "published_at": "2026-07-22 00:00:00+00:00", "updated_at": "2026-07-22 18:09:16.646187+00:00", "lang": "en", "topics": ["ai-products", "ai-tools", "natural-language-processing", "developer-tools"], "entities": ["Vercel", "AI Gateway", "AI SDK", "OpenAI", "gpt-realtime-whisper", "xAI", "grok-stt"], "alternates": {"html": "https://wpnews.pro/news/ai-gateway-now-supports-streaming-transcription", "markdown": "https://wpnews.pro/news/ai-gateway-now-supports-streaming-transcription.md", "text": "https://wpnews.pro/news/ai-gateway-now-supports-streaming-transcription.txt", "jsonld": "https://wpnews.pro/news/ai-gateway-now-supports-streaming-transcription.jsonld"}}