# Zoom Transcription API | Speaker-Labelled Transcripts

> Transcribe any Zoom meeting from one API call. A bot joins from the link and returns a speaker-labelled transcript, live during the call or after it, from $0.45 per hour all-in.

Source: https://meetstream.ai/meeting-transcription-api/zoom

## Zoom Transcription API to Transcribe Any Zoom Call

A Zoom transcription API sends a bot into the call and returns a speaker-labelled transcript, live while people speak or after the call. From $0.45 per hour all-in.

### What is a Zoom transcription API?

A Zoom transcription API turns a live Zoom call into text your code can use. One request, and the transcript arrives at your webhook.

It does two jobs: capture the audio out of the meeting, then convert it to text. The meeting transcription API covers all three platforms.

### What you get from every Zoom call

One request in. Speaker-labelled text out, live while the call runs or once it ends.

### Where Zoom speaker labels come from

Speaker identity comes from the audio channel, not from a model reading a mixed track.

Zoom gives full isolation, so every participant arrives on their own audio stream and each file holds one microphone.

An utterance carries a name because of the channel it arrived on. The speaker diarization entry sets out the other model.

### Choose a transcription engine for Zoom

MeetStream ships its own engine and routes audio to a provider you choose. Each figure below is that provider's own published number.

| Engine | Published language support | Real-time | Best for |
|---|---|---|---|
| MeetStream engine | In-house, auto language detection | No, post-call | One vendor, one bill, no extra key |
| AssemblyAI | 99 languages on Universal-2 | Yes | Broadest published language list |
| Gemini | 97 languages on the Live API | Yes | Teams already building on Gemini |
| Deepgram | 10 languages in real-time multilingual mode | Yes | Low-latency streaming workloads |
| Sarvam | 11 Indic languages plus English | No, post-call | Indian languages and accents |
| JigsawStack | Auto-detect or 162 languages | No, post-call | Batch jobs on a Whisper stack |

Live transcripts on Zoom run through Deepgram or AssemblyAI streaming, alongside five post-call engines.

### Which Zoom rules affect transcription?

Six Zoom rules decide what a transcription bot may do. Each one links to Zoom's own documentation.

| Zoom rule | What it means for a bot |
|---|---|
| Cloud recording plan | Needs Pro, Business, Education or Enterprise. Local recording is available on free accounts. |
| Who may record natively | The host or a co-host only. The host can grant a participant the right. |
| Recording disclaimer | For external participants it cannot be disabled or customised at all on any plan. |
| OBF tokens, since 2 March 2026 | A participant must have authorized your app and already be in the meeting. |
| Waiting Room | Join before host will not work. The bot waits to be admitted like anyone else. |
| Consent | Zoom's API License and Terms of Use put the duty on the developer. |

### How a Zoom bot starts transcribing

Zoom asks the host before a bot records. The bot sits in the participant list under the name you choose, and requests permission.

Grant it and capture begins, with text following straight after. Participant events tell your app which branch happened.

### From a Zoom link to your product

One request puts a bot in the call. Text streams while people speak, then a webhook says the final transcript is ready.

### Transcribe a Zoom meeting with one request

Post the meeting link and name an engine. The bot joins, transcribes, and fires a webhook when the call ends.

### Can I get a Zoom transcript without a bot?

Zoom returns transcripts of its own, on Zoom's terms. A bot sits above them.

Zoom's transcript retrieval depends on cloud recording being enabled, the right account tier and host permission, and it returns text after the meeting.

A bot captures the audio directly and can stream text while the call runs. The Zoom bot API page sets both routes side by side.

### Live transcripts and the final record

Both come off the same bot. The question is when you need the words.

The Zoom integration page covers the one Marketplace app you register before your first bot.

### Zoom transcription API pricing

Capture costs $0.35 per bot-hour and transcription adds $0.10, so a transcribed meeting is $0.45 per hour all-in.

The rate falls toward $0.25 per bot-hour at volume, and every account starts with $5 of free credit. The pricing page has the full breakdown.

The comparison hub sets MeetStream beside the other meeting bot vendors, on their own published rates.

### Zoom transcription limits and defaults

Transcripts are kept for thirty days by default, or written into your own S3 bucket from the first byte.

### One integration for all three platforms

The same request, the same webhook, the same transcript. Only the link changes.

### Zoom transcripts on any account, including your customers'.

One request captures the audio and returns the words, live or after the call.

### Got a question? We got the answer.

Common questions about transcribing Zoom calls. Where labels come from, which engines run, and what it costs.

**Can I transcribe a Zoom meeting through an API?**

Yes. One request puts a bot in the Zoom call, captures the audio, and returns a speaker-labelled transcript to your webhook.

**Does Zoom transcription need a paid plan?**

Zoom's own transcript retrieval is tied to cloud recording, account tier and host permission. A bot captures the audio directly, on any host plan.

**Are Zoom speakers labelled without diarization?**

Yes. Zoom gives a separate audio stream per participant, so each utterance carries the platform's own participant identity rather than a model's guess.

**Can I get a live Zoom transcript during the call?**

Yes. Choose a streaming engine and text chunks arrive at your webhook while people are still speaking. Deepgram and AssemblyAI both stream on Zoom.

**Which transcription engines work on Zoom?**

The MeetStream engine plus AssemblyAI, Gemini, Deepgram, Sarvam and JigsawStack. Pick one per request and the rest of your code stays the same.

**Can I have both a live and a final Zoom transcript?**

Yes. Stream during the call with a streaming engine, then re-run the recording through a post-call engine for the stored record.

**What does a Zoom transcript contain?**

A list of utterances, each tied to a named participant with start and end times, so a summary or a search index needs no extra speaker step.

**How much does the Zoom transcription API cost?**

Capture is $0.35 per bot-hour and transcription adds $0.10, so $0.45 per hour all-in, falling toward $0.25 at volume. Every account starts with $5 of credit.

### Keep exploring

### Transcribe your next Zoom call

$5 of free credit, self-serve API keys, and no sales call between you and your first transcript.

---

Full site index for agents: https://meetstream.ai/llms.txt
API contract (OpenAPI 3.1): https://meetstream.ai/openapi.json
MCP discovery: https://meetstream.ai/.well-known/mcp