Otter.ai automation
Import recordings into Otter.ai for transcription
A call was recorded somewhere other than Otter, such as a dialer or a cloud folder, and the file has to be uploaded by hand before you can search it or get action items.
Cotlet does it in your own Otter.ai account with import_audio, get_conversation and list_action_items, called by your AI agent, an n8n workflow or a script.
Hosted · nothing to install or maintain
Can Otter.ai do this on its own?
Otter offers three ways in (checked 16 Oct 2026): the Import button, a Zapier action that you set up and own, and the public API call POST /conversations, which takes a file URL and an optional name but is available to Enterprise workspaces only. The official MCP server cannot import. Nothing waits for the transcript and hands back the summary and action items.
How you do it in Otter.ai today
- On the Otter home page, click Import in the upper right and select Browse, or drag the file in.
- Otter uploads the file and starts transcribing; you can close the pop-up and track progress in the lower left corner.
- On Business or higher you can import from Dropbox instead of your computer.
- When processing ends, the transcript, summary, action items and outline are on the conversation page.
- To import files automatically, a user sets up a Zap with the Otter.ai action Import New Recordings Into Otter and pastes an API key created under Integrations.
How to import recordings into Otter.ai for transcription
Import this recording into Otter as "Discovery call 14 Oct", wait until the transcript is ready, then give me the summary and the action items. - 01
Check the link first
Your agent opens the file URL without credentials. Otter's own guide warns that a private link or one behind special permissions cannot be fetched, so a link that needs a login is rejected before it costs an import.
- 02
Check size and format
The file has to be under 5 GB and in a supported audio or video format such as MP3, M4A, WAV, MP4 or MOV. Anything else is reported with the reason instead of being sent.
- 03
Mind the plan limits
On the Basic free plan Otter allows three imported files per account and 300 transcription minutes per month. The agent names those limits before the first import and stops when Otter refuses one, so a refused import is never retried in a loop.
- 04
Import once
import_audio sends the file under the name you gave. It uses your plan's transcription minutes, so it asks for your OK by default, and the agent never retries an import it cannot confirm failed.
- 05
Wait, then report
The agent calls get_conversation until the summary and action items are marked finished, then returns both. A file still processing when the agent stops waiting is reported with its conversation link, not imported again.
What you get back
Imported "Discovery call 14 Oct" (MP3, 42 min)
Processing: finished
Summary: Customer wants a pilot for two teams starting next month; budget approval pending.
Action items: 2
- Send pilot proposal by Friday
- Book follow-up with the IT lead Other ways to ask
- Import these three recordings from the shared folder links below, named by call date, and list their summaries.
- Import the recording and wait for the transcript, but do not share it with anyone.
- Import the recording under the name of the calendar event and tell me how long the transcript took.
- Import the recording, then search all my conversations for earlier calls with the same company.
What Otter.ai allows, and what to know first
- Otter accepts imported files up to 5 GB, and each import counts toward the transcription and recording limits of your plan.
- Supported audio formats include MP3, M4A (including Apple Voice Memos), WAV, WMA, OGG and AAC; video formats include MP4, MOV, AVI, MPEG and WMV.
- On the Basic free plan you can import three audio or video files per account (not per month), transcribe up to 300 minutes per month, and view up to 30 minutes of each transcription.
- On Basic, deleted conversations still count toward the monthly transcription limit.
- Business or higher plans can import without a file count limit, up to 6,000 minutes per month.
import_audio asks for your OK by default. To run it on a schedule without you, switch confirmation off for that tool in your dashboard.
Sources: Otter Help: Import an audio or video file · Otter Help: Import limits on the Basic free plan · Otter Help: Import recordings automatically using Zapier · Otter Help: Otter.ai Public API
Call import_audio from a script
curl -X POST https://cotlet.dev/api/v1/otter/audios \
-H "Authorization: Bearer $COTLET_API_KEY" \
-H "Content-Type: application/json" \
-d '{"file_url":"https://example.com/recordings/discovery-call.mp3","name":"Discovery call 14 Oct"}' {
"conversation_id": "cv_a7710e",
"name": "Discovery call 14 Oct",
"status": "processing"
} MCP: add https://cotlet.dev/mcp/v1 with the same key; the call is otter_write → import_audio. Example data.
Schedule it in n8n, Make, Zapier or cronOtter.ai tools this automation uses
| Tool | Parameters |
|---|---|
| import_audio | file_url, name |
| get_conversation | conversation_id |
| list_action_items | conversation_id, status, limit, cursor |
Frequently asked questions
Is it safe to connect Otter.ai to Cotlet?
Yes. You sign in to Otter.ai yourself, in your own Cloud Browser in the EU, and we never save your password. Your agents only get Otter.ai once you enable it, every background request is listed, and the browser profile is stored encrypted with AES-256-GCM, the cipher 1Password uses for its vaults. The AI model never sees a login, posts and messages wait for your OK, and Disable for agents cuts access in one click. Independent scanners grade cotlet.dev A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory; live results are on https://cotlet.dev/security.
Give your agent access to Otter.ai.
Free 7-day trial with 2,000 credits, no card needed. Cotlet is independent and not affiliated with Otter.ai.