> For the complete documentation index, see [llms.txt](https://docs.screendesk.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.screendesk.io/debug-with-ai/ai-transcripts.md). # AI transcripts Search spoken content, jump to timestamps, and copy or export transcripts from eligible recordings. AI transcripts turn the spoken content of an eligible recording into searchable, timestamped text. Use them to find the customer's exact wording, jump to a relevant moment, or copy context into a ticket. ## Before you start The workspace must have transcript access and **AI processing** enabled. The recording must contain detectable speech. Recorded video calls can also have transcripts when live transcription is enabled and recording consent permits processing. Availability depends on the workspace's settings and features. See [AI settings](/debug-with-ai/ai-settings.md) for the workspace-wide processing control. ## Open and use a transcript Open the recording, then select **Transcript** in the recording's side panel. | Control | What it does | | ------------------------- | ------------------------------------------------------ | | **Search transcript** | Finds words or phrases and highlights matches | | **Previous / next match** | Moves between search results | | **Timestamped segment** | Seeks the video to that moment | | **Copy** | Copies the transcript | | **Copy snippet** | Copies an individual segment | | **Download** | Exports SRT captions when a caption file is available | | **Auto-scroll** | Follows playback through the transcript; can be paused | ## Transcripts and summaries A transcript is the spoken content. [Report intelligence](/debug-with-ai/ai-summary.md) provides a summary and other findings from the evidence available in the report. A silent screen recording can still have useful visual analysis even though there is no spoken transcript. ## If a transcript is missing Check that the recording contains speech, processing has completed, and the relevant workspace settings are enabled. For recorded calls, also check live-transcription settings and recording consent. Processing time varies with the recording. Long recordings can take longer; there is no fixed completion time. Turning off AI processing stops new speech processing while existing transcripts remain available. Turning it back on does not automatically backfill every old recording. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.screendesk.io/debug-with-ai/ai-transcripts.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.