OpenAI Responses API and Agents SDK · TranscriptFetch docs

Give GPT models video transcripts as a tool: the TranscriptFetch MCP server in the Responses API and the Agents SDK, with tested examples.
Works with OpenAI. The TranscriptFetch MCP server plugs into OpenAI's Responses API and the Agents SDK as a remote MCP tool, so a GPT model can read video transcripts, search YouTube, TikTok and Instagram, and list channels and playlists on its own. Every example on this page was run against production on 2026-10-20. Credits are the same as the API: one per successful caption fetch or listing page, AI Fallback Transcription 1 credit per started 5 minutes of audio, and failed requests are free.
OpenAI's servers call TranscriptFetch for you during the response. Pass the key in the tool's authorization field. OpenAI does not store that value, so send it with every request.
The same request with curl:
The SDK offers the same hosted tool, or a local connection where your own process calls TranscriptFetch and the key never leaves your server.
Hosted (OpenAI calls TranscriptFetch, as in the Responses API):
Local (your process calls TranscriptFetch):
The monitor tools are the only ones that change the account: create_monitor and check_monitor_now are writes that spend credits, and delete_monitor is destructive. The server marks them so in its tool annotations, and asks the assistant to confirm with you before creating or deleting a monitor. ChatGPT is not offered them yet.
Timestamped segments repeat every word with its timings. When the model only needs the words, have it call get_transcript with timestamps: false (say so in the agent's instructions), or send "timestamps": false to the REST API. Plain text uses about two-thirds fewer tokens than the same transcript as SRT, WebVTT or YouTube's caption XML: the median saving across 9 videos from 20 seconds to 2 hours was 64 to 67%, counted with OpenAI's o200k tokenizer. Keep the segments when answers need timestamps to cite.