Skip to main content

Documentation Index

Fetch the complete documentation index at: https://api-docs.tiro.ooo/llms.txt

Use this file to discover all available pages before exploring further.

Five copy-pasteable scenarios that cover most everyday CLI workflows. Each runs in under 30 seconds against a populated tenant.

​
1. List your most recent notes

tiro notes list --limit 10
Pretty output in a TTY: 
2026-04-02  note-a8f2c1...  18m32s  Q3 Planning
2026-04-01  note-b7e1d4...  12m05s  Customer call with Acme Corp
2026-03-29  note-c3f9a2...  45m11s  Engineering weekly standup
…
Add --json to switch to NDJSON for piping: 
tiro notes list --limit 100 --json | jq -r '.guid' | head -5

​
2. Search by keyword and date range

tiro notes search "OKR" --since 30d --json
tiro notes search uses Tiro’s deep search — each result is a note hydrated with its primary documents (one-pager, custom). The keyword is required (positional or --keyword). Date filters accept ISO-8601 or relative shorthand: 
tiro notes search "Q3 Planning" --since 2026-04-01 --until 2026-05-01
tiro notes search "Acme Corp"   --since 7d
tiro notes search "release"     --since 24h
Folder-scoped: 
tiro notes search "deploy" --folder <folderId> --json

​
3. Save a single meeting note as Markdown

tiro notes get <noteGuid> --output ./q3-planning.md --include transcript
stdout returns one line of metadata — the actual content goes to disk: 
{"ok":true,"data":{"saved":"./q3-planning.md","size":12450,"format":"md","guid":"note-a8f2c1...","title":"Q3 Planning"}}
The Markdown file contains a YAML frontmatter, the participant list, and a transcript block with speaker headers and elapsed timestamps: 
**[Yeoul, 00:12]** Let's start with the Acme deal pipeline.
**[Evan, 00:18]** They just signed the LOI.

​
4. Pipe search results to jq

tiro notes search "OKR" --since 7d --json \
  | jq -r 'select(.recordingDurationSeconds > 600) | .guid' \
  > long-okr-meetings.txt
--json always emits NDJSON for list/search responses — one note per line. Combine with jq -c (compact) for further pipelines, or head / tail to slice. If the response includes a next-page cursor, it’s emitted as a final NDJSON line keyed _cursor: 
tiro notes list --limit 50 --json | tail -1
# → {"_cursor":"eyJjcmVhdGVkQXQi…"}
Pass that back as --cursor to continue: 
tiro notes list --limit 50 --cursor "eyJjcmVhdGVkQXQi…"

​
5. Get a transcript with speaker labels

tiro notes transcript <noteGuid> --format md --output ./transcript.md

# Customer call with Acme Corp

**Participants**: Yeoul, Evan, Hailey

## Transcript

**[Yeoul, 00:00]** Thanks for joining — let me walk through the proposal.
**[Hailey, 00:12]** One quick question on pricing tiers.
**[Evan, 00:25]** That's covered on slide 4.
…
For agents that already understand MCP’s get_note_transcript payload, switch to --format json — the shape is byte-for-byte identical: 
tiro notes transcript <noteGuid> --format json

{
  "noteGuid": "note-a8f2c1...",
  "title": "Customer call with Acme Corp",
  "participants": ["Yeoul", "Evan", "Hailey"],
  "createdAt": "2026-04-01T10:30:00Z",
  "recordingDurationSeconds": 3605,
  "paragraphs": [
    {
      "timeFrom": "2026-04-01T10:30:00Z",
      "timeTo":   "2026-04-01T10:30:12Z",
      "segments": [
        { "content": "Thanks for joining…",
          "speaker": { "label": "SPEAKER_0", "name": "Yeoul" } }
      ]
    },
    …
  ]
}
→ Continue to For AI agents for tool-selection guidance and worked agent flows.