# Scribe API

<!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->

The Scribe API transcribes audio and video in Fast, Batch, and Live modes. It can also return polished text when you enable [Text Polishing](/docs/ai-services/scribe/text-polishing/).

## Key features

-   Processes common audio and video formats in Fast and Batch modes
-   Streams real-time audio and transcription events in Live mode
-   Provides Captions (partial transcription results) before a Live transcript item completes **_(Partial results feature in preview)_**
-   Returns display text and transcript segments
-   Includes optional segments, word timestamps, speaker labels, channel numbers, and detected languages, depending on the mode and configuration
-   Supports mono and stereo inputs with optional channel separation
-   Recognizes ten languages with the `zoom-scribe-multilingual` model and 26 additional locales with the `whisper` model
-   Improves recognition of names and domain terms with custom vocabulary
-   Produces optional [Text Polishing](/docs/ai-services/scribe/text-polishing/) output for `en-US`
-   Preserves timestamps and source metadata from [Zoom RTMS](/docs/rtms/)

> **Partial results feature in preview**
>
> The partial results feature is still in preview and may not work as documented.

## Processing modes

| Mode                                          | Transport         | Use case                                                                        |
| --------------------------------------------- | ----------------- | ------------------------------------------------------------------------------- |
| [Live](/docs/ai-services/scribe/live-mode/)   | WebSocket         | Real-time captions, agents, RTMS applications, and other streaming experiences. |
| [Fast](/docs/ai-services/scribe/fast-mode/)   | Synchronous HTTP  | Individual files that need an inline result.                                    |
| [Batch](/docs/ai-services/scribe/batch-mode/) | Asynchronous HTTP | Long recordings and collections of files in object storage.                     |

All three modes support transcription, model selection, language configuration, and vocabulary customization. Text Polishing is available in each mode, with mode-specific response behavior.

For higher English accuracy, select the Pro option, **Scribe API Pro High-Accuracy**, with the model ID `zoom-scribe-en-pro`.

## Speech configuration

Scribe does not create conversation summaries, meeting notes, or action items. Pass a completed transcript to the [Summarizer API](/docs/ai-services/summarizer/) when your application needs those artifacts.

For recognition settings, language coverage, and model selection, see [Speech configuration](/docs/ai-services/scribe/speech-configuration/).

## Speaker diarization and channel separation

Speaker diarization and channel separation describe different aspects of the audio:

-   `diarization` identifies speakers from characteristics of their speech and adds a speaker label to transcript segments.
-   `channel_separation` processes the left and right channels of a stereo input independently and adds a channel number to each segment.

You can enable either or both options. For best diarization results, use recordings with fewer than 20 speakers.

## Supported media formats

Fast and Batch modes accept these containers:

-   WAV
-   M4A
-   MP3
-   MP4
-   WebM

Audio can be mono or stereo with a sample rate of at least 8 kHz. We recommend a sample rate of 16 kHz or greater.

## Resources

AI Services are part of the [Zoom Build platform](/docs/build/). Use [Zoom.ai](https://zoom.ai/) to create a project, get credentials, and manage your AI Services plan.