Skip to main content

Get started

Start with the basics. Learn what Audio Dictation is, how it differs from Ambient note generation, and which APIs or SDKs fit your stack.

Audio Dictation Overview

Learn about Audio Dictation, when to use it, and how to integrate it

Audio Dictation

Learn about Dictation capabilities, workflow, and where transcript text lands in your application

Dictation API Overview

Orient to Ambient and Dictation Partner APIs, auth, and core resources

Dictation API Quickstart

Create a session and stream Dictation audio end to end

Dictation Basic Usage

Create a Dictation session, stream audio, and retrieve transcription results

Dictation SDK

Embed Dictation with Suki’s hosted iframe UI for JavaScript and React

Web SDK for Dictation

Use Dictation in the Web SDK when you already embed the headed Web SDK

Stream Dictation audio

After you create a Dictation session with the Partner APIs, stream audio over WebSocket and handle partial and final transcript frames.

Dictation Streaming

Stream Dictation audio over WebSocket after you create a session

Dictation Streaming Transcripts

Learn how partial and final transcription frames arrive during a Dictation stream

Dictation Wire Format

Dictation-specific WebSocket frames, fields, and message examples

Resources

Refer to these pages when you need tutorials, decision help, FAQs, or partner support.

Dictation WebSocket Tutorial

Build a Dictation streaming client with a full code example

Integration Decision Guide

Choose Dictation APIs or SDKs based on your app type and stack

Dictation SDK FAQs

Find answers to general, integration, and technical questions for the Dictation SDK

Platform FAQs

Find answers to general, authentication, and security questions

Support

Contact Suki for partner documentation and SDK support

Last modified on August 13, 2026