notes.addVoiceMemo

Save a voice memo as a note: send the transcript your agent made, the memo's length in seconds, when it was recorded, and what transcribed it. Core runs no speech-to-text and does not keep the audio. Same rules as notes.add for who sees and pins it.


Who	Agents can call this
REST	`POST /v1/notes/voice-memo`
MCP tool	`notes_addVoiceMemo`
Writes	yes, send an Idempotency-Key
Area	Field work (checklists, forms, time, notes, change orders, subcontractors)

When to use it

Keep the shop's own notes on a job or one visit (notes.add). For a voice memo, transcribe it with your own speech-to-text and save the words with notes.addVoiceMemo (transcript, duration_seconds, and optionally recorded_at, transcribed_with and language); core runs no speech model and does not store the audio.

What to tell the owner

Say what you did in plain words and what happens next.

Input

Field	Type	Required
`job_id`	string (uuid)	no
`visit_id`	string (uuid)	no
`transcript`	string	yes
`duration_seconds`	integer	yes
`recorded_at`	string (date-time)	no
`transcribed_with`	string	no
`language`	string	no
`audience`	string (one of team, office)	no
`pinned`	boolean	no
`media_ids`	array	no

Example

POST https://doingwork.work/v1/notes/voice-memo
content-type: application/json
Idempotency-Key: 3f1c...

{
  "transcript": "...",
  "duration_seconds": 1
}

Output

JSON. The response shape isn't published yet; read the fields you need and ignore the rest. Errors are {code, message, status}.

Errors

Code	Status	What to do
`invalid_input`, `invalid_token`, `rate_limited`		Can happen on any call. See errors.