AI Gateway now supports streaming transcription
Quick Answer
AI Gateway now enables streaming transcription, allowing real-time audio input and immediate transcript updates with models like 'openai/gpt-realtime-whisper'.
Quick Take
This beta feature enhances applications such as live captioning and voice input, maintaining low latency and compatibility across various streaming-capable models.
Key Points
- Streaming transcription is available in beta via the AI SDK's streamTranscribe function.
- Users can stream audio and receive transcript updates as they are generated.
- Compatible with various models, including 'xai/grok-stt' and 'openai/gpt-realtime-whisper'.
- Enables voice mode for agents, allowing real-time speech-to-text processing.
- Documentation provides further details on implementing streaming transcription.
Source Excerpt
AI Gateway now supports streaming transcription. Stream live audio and get transcript updates back as they're produced, using the AI SDK's streamTranscribe.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from Vercel AI
See more →
The Agent Stack
The Agent Stack by Vercel AI provides essential building blocks for creating production-grade agents, enabling seamless integration across multiple AI models and secure operations. It features components like AI Gateway for model routing, Workflow SDK for durable execution, and Vercel Connect for scoped access, streamlining agent development and deployment across various platforms.
