Migrate from Whisper to GPT-Transcribe and GPT-Live-Transcribe

# Migrate from Whisper to GPT-Transcribe and GPT-Live-Transcribe ## Overview OpenAI’s new transcription models give existing Whisper users two focused upgrade paths. GPT-Transcribe (`gpt-transcribe`) is designed for accurate transcription of completed audio via uploaded files. GPT-Live-Transcribe (`gpt-live-transcribe`) is designed for low-latency, continuously streaming transcription. At a high level, the API endpoints are the same. File requests continue to use POST /v1/audio/transcriptions. Realtime integrations continue to configure a transcription session and handle transcription events. What’s different are the supported request fields, the output formats, and contextual/multilingual hints. ### What stays the same - File transcription uses the existing Audio API transcription endpoint. - Realtime transcription uses the existing Realtime transcription session, WebSocket or WebRTC transport, and transcription events. - Applications still provide audio, receive transcription text, and handle API or connection errors. ### What changes - Use `gpt-transcribe` for completed files, streamed file transcripts, or committed Realtime turns. - Use `gpt-live-transcribe` for continuously streaming, low-latency live transcription. - Replace the legacy `language` hint with the new-model `languages` array. - Use `prompt` for free-form context and `keywords` for literal terms expected in the audio. - Handle detected-language output for GPT-Transcribe, including an empty languages array. ## 1. Choose your migration path - Recorded meetings, calls, or uploaded audio: migrate `whisper-1` to `gpt-transcribe` on POST /v1/audio/transcriptions. - Live captions or continuously arriving microphone audio: migrate `gpt-realtime-whisper` to `gpt-live-transcribe` in a Realtime transcription session. - Higher-accuracy transcription after a manually committed audio turn: use `gpt-transcribe` in a Realtime transcription session over WebSocket. Treat live audio and streaming output as separate decisions. A completed file can produce streamed transcript events, and a Realtime session can wait for an audio turn to be committed before producing deltas. ## 2. Migrate recorded audio The smallest file migration preserves the endpoint, SDK call, and file upload. Replace the model identifier, then consume the JSON transcription response.