Speech to Text › Minutes of meetings

Minutes of meetings

Structured transcription for Arabic meeting recordings. Upload meeting audio and get clean, readable output with duration and word-level timestamps — consistent Arabic meeting records ready for documentation and follow-up actions.

Endpoint

POST /api/v1/minutes-of-meeting/transcribe

Authenticate with your API key in the x-api-key header. See Authentication.

Header	Value
`x-api-key`	YOUR_MUNSIT_API_KEY

Upload the recording.

bash

curl -X POST "https://api.munsit.com/api/v1/minutes-of-meeting/transcribe" \ -H "x-api-key: $MUNSIT_API_KEY" \ -F "file=@standup.mp3" \ -F "model=munsit"

Response — 200

{ "statusCode": 200, "data": { "transcriptionId": "805059bf-7c3f-4a1e-9d2b-1f0c6ae83b47", "transcription": "لك كلما عمقت الآخرين أصبحت قزما...", "duration": 53.661375, "timestamps": [ { "word": "الأشياء", "start": 0.24, "end": 0.31 } ] }, "message": "Success" }

Request

Send the body as multipart/form-data. Processing is asynchronous and optimized for pre-recorded meeting audio: upload the recording, Munsit analyzes the content and generates a structured transcript, and you receive organized output with timing for easy review.

Field	Type	Required	Description
`file`	file	Yes	Meeting recording audio file — see supported formats.
`model`	string	No	ASR model to use: `munsit` (default) or `munsit-en-ar` (mixed Arabic-English with code-switching).

30-minute limit. Minutes of Meetings supports files shorter than 30 minutes. For longer recordings, split the audio into shorter segments for best performance.

Transcribe-only options. hotwords and return_confidence apply to POST /audio/transcribe only.

Response fields

The payload arrives under data, alongside statusCode and message.

Field	Type	Description
`transcriptionId`	string (UUID)	Meeting transcription ID.
`transcription`	string	Full transcript.
`duration`	number	Audio duration in seconds.
`timestamps`	array of objects (`word`, `start`, `end`)	Word-level timing.
`originalTranscript`	string	Raw verbatim transcript, before summarisation.
`summary`	string	Generated meeting summary.
`attributes`	object	Internal metadata blob persisted with the transcription. Prefer the named fields — treat this as unstable.
`audioUrl`	string	Stored copy of the uploaded audio. See Audio retention.
`stats`	object (`fileName`, `fileSize`, `mimeType`, `creditsConsumed`)	Upload metadata and the credits billed for this request.

Go further

Downstream analysis and the other shapes of transcription.

Keyword extraction →Pull agenda topics and action items out of the meeting.POST /keyword-extraction Diarization →Who said what — speaker-labeled meeting segments.POST /audio/diarization/transcribe Transcribe →General-purpose transcription for files under 60 minutes.POST /audio/transcribe Sentiment analysis →How the meeting felt, not just what was said.POST /sentiment-analysis

Working with an AI assistant? Every page is available as Markdown: add .md to the URL, or send an Accept: text/markdown header. For the whole documentation in one request, point it at llms-full.txt; the page index is llms.txt. Or use Copy Page, top right.