Meetings
Shared spoken notes from customer calls, one-on-ones, and team meetings.
This is where decisions, questions, and follow-ups show up.
Agent memory
Give your agent spoken context without giving up the files.
Transcripted saves meetings and dictation as local Markdown transcripts with structured frontmatter and a searchable capture folder your agent can read.
The missing context
Agents usually know what you typed. They miss what was said out loud.
Transcripted closes that gap by saving spoken context as local files you can keep and reuse.
Meetings + dictations
One captures the room. The other captures your thinking.
Meetings capture what happened. Dictation captures what you want to remember next.
Dictations
Private voice notes from quick thoughts, recaps, and post-meeting follow-ups.
This is where you save what you think happened and what to do next.
Together
Meetings and dictations give your agent both the shared record and your own notes.
Transcripted starts with meetings and gets better as you add the voice notes that connect the dots.
What your agent gets
Readable transcript
A clean transcript with timestamps and speaker names.
YAML frontmatter
Dates, duration, capture type, engines, speakers, and source details live at the top of the Markdown file.
Capture folders
Meetings and dictations are saved in predictable local folders that agents can search.
Persistent speaker identity
The same person can stay linked across meetings.
How it connects
Start with files. Add MCP or the CLI when you need more direct access.
Files first
Point Claude, Cursor, Obsidian, or any file-reading tool at your local Transcripted folder.
Starter prompt
Transcripted can generate a simple prompt that tells your agent where the files live.
Read-only MCP
On supported agents, the local MCP server lets you search, recap, and read meetings or dictations.
CLI and automation
Developers can use the standalone CLI context commands or script against the same local Markdown files.
What your agent can answer
"What did we decide about pricing last Tuesday?"
Three customer meetings and one follow-up dictation all point to the same call: keep annual pricing manual for now, and let Sarah run the next test.
"What has Sarah committed to this quarter?"
Her main commitments keep coming back to onboarding tracking, the activation rewrite, and a partner rollout.
"Summarize every discussion about the API migration."
The meetings show the plan moving from open questions to a clear order of work, then a dictation that locks in the launch plan.
"What follow-ups came out of my last three customer calls?"
The same follow-ups came up again and again: onboarding time, reporting exports, and enterprise approvals.
"Who keeps raising concerns about onboarding time?"
The same two people keep bringing it up, and your dictations keep tying it back to activation drop-off.
Why local matters for agents
If your meeting history only lives inside a vendor, your agent is limited by that vendor's API and retention model.
Transcripted starts with files you own, then adds a starter prompt, MCP, and the CLI on top.
Compatible workflows
Claude Desktop and file-reading agents
Point the tool at your local Transcripted data and start asking questions across meetings and dictations.
Supported MCP clients
Use the read-only local MCP server for search, recap, person lookup, and direct reads.
Cursor, editors, and local copilots
Keep spoken context next to the code and docs it informs.
Obsidian and second-brain workflows
Keep the Markdown in your vault while the frontmatter metadata and consistent capture folders preserve richer machine context.
FAQ
How do I use Transcripted as context for AI agents?
Start by pointing your agent at your local Transcripted data. The app can also generate a starter prompt, and supported agents can connect through the read-only local MCP server.
Does Transcripted have an MCP server?
Yes. Transcripted offers a read-only local MCP server for supported agents. You can also use the files directly without MCP.
What format does Transcripted use for agent-ready output?
Transcripted saves a readable transcript, structured YAML frontmatter, and a capture-folder layout for the broader corpus. Meetings also include persistent speaker identity over time.
Does Transcripted support dictation too?
Yes. Transcripted starts with meetings and also supports dictation, which lets you add personal spoken notes and synthesis into the same local spoken-context corpus.
What AI tools work with Transcripted?
Any AI tool that can read local files can work with Transcripted. On supported agents, the local MCP server provides a stronger direct query surface for meetings and dictations.
Give your agent spoken context it can use.
Start with local files. Add MCP when you need it.