Add AI meeting summaries to any app with Zoom AI Services in 15 minutes

A developer demonstrated how to add AI meeting summaries and action items to any application using Zoom AI Services, Zoom's developer API platform, with roughly 60 lines of Python and two REST calls. The tutorial covers the Scribe transcription endpoint (Fast mode for files up to 5 minutes, Batch for up to 6 hours, Live over WebSocket), which supports 9 locales, speaker diarization, and word-level timestamps via query parameters, then feeds the speaker-labeled transcript to a Summarizer. The author stresses that API keys are server-to-server only and must never ship in client-side code.

If you have meeting recordings standups, sales calls, support calls and you want summaries + action items out of them without running your own speech models, two REST calls are all it takes: Both are part of Zoom AI Services , Zoom's developer API platform. The developer portal lives at zoom.ai https://www.zoom.ai/ verified October 2026 — that's Zoom's own portal, not a third party . No SDK needed — it's plain REST. Total code: about 60 lines of Python. requests pip install requests . That's it for credentials. One important rule: API keys are server-to-server only. Never put the key in client-side code or ship it in a mobile/web app bundle. All calls in this tutorial run from a backend. Not ready to create a key? The portal has an interactive playground with sample data — no setup required. I'd suggest poking it for two minutes so you know what the responses look like before wiring up the script. Scribe has three modes: Live real-time transcription over a secure WebSocket at wss://api.zoom.us/v2/aiservices/scribe/live , Fast synchronous — POST your audio bytes, the response returns when transcription completes , and Batch async jobs API for long files, with webhook callbacks . For this tutorial we use Fast mode , the simplest. Fast mode handles files up to 5 minutes ; longer recordings go through Batch up to 6 hours per file . Input is the raw audio bytes: WAV, Opus, and µ-law encodings audio/wav , etc. via Content-Type . 9 locales: en-US , de-DE , es , fr-FR , it-IT , ja-JP , ko-KR , pt-BR , zh-CN . Endpoint: POST https://api.zoom.us/v2/aiservices/scribe/transcribe Auth: one header — x-api-key: <your API key . That's the whole auth story per the portal docs. Options go as query parameters model , language , diarization , text polishing , profanity filter , word time offsets , channel separation , custom terms : curl -X POST "https://api.zoom.us/v2/aiservices/scribe/transcribe?model=zoom-scribe-en&language=en-US&diarization=true&text polishing=true" \ -H "x-api-key: $ZOOM API KEY" \ -H "Content-Type: audio/wav" \ --data-binary @meeting.wav Setting diarization=true adds a speaker label Speaker 1 , Speaker 2 , … to each segment — worth it for meetings. Set Content-Type to match your file. Response 200 — synchronous; it returns after transcription completes: { "request id": "req 123", "duration sec": 181.04, "result": { "text display": "So, let's have a good conversation, my friend. Do you think...", "segments": { "id": "seg 1", "start": 0.0, "end": 5.2, "channel": 1, "speaker": "Speaker 1", "text": "So, let's have a good conversation, my friend.", "words": } }, "model": "zoom-scribe-en", "usage": { "input units": 181.04, "unit type": "seconds" } } With word time offsets=true the words arrays carry per-word timestamps; channel separation=true splits stereo channels. In Python: python import os, requests API BASE = "https://api.zoom.us/v2/aiservices" API KEY = os.environ "ZOOM API KEY" def transcribe audio path: str, language: str = "en-US" - dict: with open audio path, "rb" as f: audio bytes = f.read resp = requests.post f"{API BASE}/scribe/transcribe", headers={"x-api-key": API KEY, "Content-Type": "audio/wav"}, params={"model": "zoom-scribe-en", "language": language, "diarization": "true", "text polishing": "true"}, data=audio bytes, timeout=300, resp.raise for status return resp.json "result" Tip: feed the Summarizer a speaker-labeled transcript — it's much better at action-item ownership. Build it from the segments: php def segments to transcript result: dict - str: lines = for seg in result.get "segments", : speaker = seg.get "speaker" or "Speaker" lines.append f"{speaker}: {seg.get 'text', '' .strip }" text = "\n".join lines return text or result.get "text display", "" The Summarizer API takes transcript text from any system — it doesn't have to come from Scribe and returns rendered, display-ready text in result.text . Fast mode accepts one inline transcript up to 96 KB and returns synchronously. Endpoint: POST https://api.zoom.us/v2/aiservices/summarizer/summarize The request is flat JSON — no config wrapper. transcript is a JSON-encoded string of speaker/text turns: curl -X POST https://api.zoom.us/v2/aiservices/summarizer/summarize \ -H "x-api-key: $ZOOM API KEY" \ -H "Content-Type: application/json" \ -d '{ "summary type": "CONVERSATION", "task": "full summary", "transcript": " {\"speaker\": \"Speaker 1\", \"text\": \"Let us finalize the timeline.\"}, {\"speaker\": \"Speaker 2\", \"text\": \"We need one more week for validation.\"} ", "language": "en-US" }' Four tasks to choose from, set in task : | task | What result.text contains | |---|---| | recap | A concise Recap: paragraph | | summary | A detailed Summary: section | | action items | An Action Items: section grouped by owner | | full summary | All three — recap + summary + action items | summary type is "CONVERSATION" default; also "GENERIC" , "MEETING NOTES" , language is a BCP-47 output locale 14 supported, en-US default . Response 200 — the exact shape, from the official docs: { "request id": "req 123", "task": "full summary", "result": { "text": "Recap:\n\nThe team agreed to delay the launch by one week.\n\nSummary:\n\n..." } } For full summary , result.text is rendered text, ready to display — recap, summary, and action items grouped by owner. php import json def summarize transcript: str, task: str = "full summary" - str: turns = for line in transcript.splitlines : if ":" in line: speaker, text = line.split ":", 1 turns.append {"speaker": speaker.strip , "text": text.strip } resp = requests.post f"{API BASE}/summarizer/summarize", headers={"x-api-key": API KEY, "Content-Type": "application/json"}, json={"summary type": "CONVERSATION", "task": task, "transcript": json.dumps turns , "language": "en-US"}, timeout=120, resp.raise for status data = resp.json result = data.get "result" or {} return result.get "text" or data.get "text" or data.get "summary" or "" One script: audio file in, meeting summary out. Save as summarize meeting.py : php /usr/bin/env python3 """Audio file - transcript - meeting summary, via Zoom AI Services Scribe + Summarizer . Usage: ZOOM API KEY=<your key python summarize meeting.py meeting.wav The key is server-side only -- never expose it to clients. """ import json, os, sys, requests API BASE = "https://api.zoom.us/v2/aiservices" API KEY = os.environ "ZOOM API KEY" def transcribe audio path: str, language: str = "en-US" - dict: with open audio path, "rb" as f: audio bytes = f.read resp = requests.post f"{API BASE}/scribe/transcribe", headers={"x-api-key": API KEY, "Content-Type": "audio/wav"}, params={"model": "zoom-scribe-en", "language": language, "diarization": "true", "text polishing": "true"}, data=audio bytes, timeout=300, resp.raise for status return resp.json "result" def segments to transcript result: dict - str: lines = f"{seg.get 'speaker' or 'Speaker'}: {seg.get 'text', '' .strip }" for seg in result.get "segments", return "\n".join lines or result.get "text display", "" def summarize transcript: str, task: str = "full summary" - str: turns = {"speaker": s.strip , "text": t.strip } for s, , t in line.partition ":" for line in transcript.splitlines if t.strip resp = requests.post f"{API BASE}/summarizer/summarize", headers={"x-api-key": API KEY, "Content-Type": "application/json"}, json={"summary type": "CONVERSATION", "task": task, "transcript": json.dumps turns , "language": "en-US"}, timeout=120, resp.raise for status data = resp.json result = data.get "result" or {} return result.get "text" or data.get "text" or data.get "summary" or "" def main - None: audio path = sys.argv 1 print "Transcribing...", flush=True result = transcribe audio path transcript = segments to transcript result print f"Transcript ready {len transcript } chars . Summarizing...\n", flush=True print summarize transcript if name == " main ": main Run it: ZOOM API KEY=your key here python summarize meeting.py meeting.wav That's the whole pipeline: audio bytes → diarized transcript → recap + summary + action items. Fast mode caps at 5 minutes of audio; longer files go through the Batch jobs API. On pricing: Zoom AI Services are usage-based via prepaid credits. I don't have verified per-minute rates, so check the current numbers at zoom.us/pricing/developer https://zoom.us/pricing/developer before you estimate costs. 401 Unauthorized. Most common causes: the key is wrong or expired remember, it's shown only once at creation — regenerate it in the portal if you lost it , or the wrong header name. Per the portal docs, auth is the x-api-key header only. Unsupported format / fetch errors. Scribe Fast mode takes the raw audio bytes --data-binary , not a URL — set Content-Type to match audio/wav , audio/mpeg , … . Keep Fast-mode files under 5 minutes; longer audio goes through Batch. 429 rate limits. Back off and retry with exponential backoff. Exact rate limits and quotas depend on your plan — check the portal rather than guessing. Diarization quality. Heavy background noise, overlapping speech, and very short clips all degrade speaker separation. If labels matter to you they should — the Summarizer groups action items by owner , a quick pass with a noise-reduction tool before upload pays off. Transcript too long for Summarizer Fast mode. Inline input caps at 96 KB . For longer meetings, split the transcript into chunks and summarize each, or move to Batch mode. GET /aiservices/summarizer/jobs/{jobId} or .../scribe/jobs/{jobId} , or get webhook callbacks. Webhooks are signed — verify with the x-zm-signature HMAC-SHA256, sha256= prefix and x-zm-request-timestamp headers against your secret. wss://api.zoom.us/v2/aiservices/scribe/live — one completed segment per detected speech turn. Disclosure: this article was drafted with AI assistance; all API calls and code were checked against the official Zoom AI Services portal docs October 2026 , and the Scribe flow was run live in the portal playground.