Pre-Recorded Audio Transcription — Deepgram

The Deepgram JavaScript SDK now works in both server and browser environments. A proxy configuration is required for browser environments (see the section below).

Installing the SDK

TypeScript

1 # Install the Deepgram JS SDK
2 # https://github.com/deepgram/deepgram-js-sdk
3 
4 npm install @deepgram/sdk

Initializing the SDK

TypeScript

1 import { createClient } from "@deepgram/sdk";
2 
3 const deepgram = createClient("DEEPGRAM_API_KEY");

Transcribing a file by URL

Any public audio or video file can be used.

TypeScript

1 const { result, error } = await deepgram.listen.prerecorded.transcribeUrl(
2   {
3     url: "https://dpgr.am/spacewalk.wav"
4   },
5   {
6     model: "nova-3"
7   }
8 );

Transcribing a file buffer

Any ArrayBufferLike can be sent as the body. This includes file buffers from Node’s fs.readFile/fs.readFileSync, or a Blob.arrayBuffer() in a browser client.

TypeScript

1 const { result, error } = await deepgram.listen.prerecorded.transcribeFile(
2   fs.readFileSync("./examples/spacewalk.wav"),
3   {
4     model: "nova-3",
5   }
6 );

Transcribing a file stream

Any ReadStream can be sent as the body. This includes a stream from Node’s fs.createReadStream.

TypeScript

1 const { result, error } = await deepgram.listen.prerecorded.transcribeFile(
2   fs.createReadStream("./examples/spacewalk.wav"),
3   {
4     model: "nova-3",
5   }
6 );

Pre-recorded Transcription Options

Transcription options are provided as an object to our transcription functions. Each of these parameters are found as unique features on the Pre-Recorded API reference.

Helper Functions

In the latest SDK version, caption formatting has been has been published as a standalone package and built into the SDK. You can use an import statement to invoke caption functionality from the stand alone caption package.

Formatting as WebVTT

JavaScript

1 import { createClient } from "@deepgram/sdk";
2 import { webvtt } from "@deepgram/captions";
3 // - or -
4 // import { createClient, webvtt } from "@deepgram/sdk";
5 
6 const deepgram = createClient("DEEPGRAM_API_KEY");
7 
8 const { result, error } = await deepgram.listen.prerecorded.transcribeUrl(
9   {
10     url: "https://dpgr.am/spacewalk.wav"
11   },
12   {
13     model: "nova-3",
14   }
15 );
16 
17 if (error) {
18   console.error(error);
19 }
20 
21 const captions = webvtt(result);

Formatting as SRT

JavaScript

1 import { createClient } from "@deepgram/sdk";
2 import { srt } from "@deepgram/captions";
3 // - or -
4 // import { createClient, webvtt } from "@deepgram/sdk";
5 
6 const deepgram = createClient("DEEPGRAM_API_KEY");
7 
8 const { result, error } = await deepgram.listen.prerecorded.transcribeUrl(
9   {
10     url: "https://dpgr.am/spacewalk.wav"
11   },
12   {
13     model: "nova-3",
14   }
15 );
16 
17 if (error) {
18   console.error(error);
19 }
20 
21 const captions = srt(result);

1	# Install the Deepgram JS SDK
2	# https://github.com/deepgram/deepgram-js-sdk
3
4	npm install @deepgram/sdk

1	import { createClient } from "@deepgram/sdk";
2
3	const deepgram = createClient("DEEPGRAM_API_KEY");

1	const { result, error } = await deepgram.listen.prerecorded.transcribeUrl(
2	{
3	url: "https://dpgr.am/spacewalk.wav"
4	},
5	{
6	model: "nova-3"
7	}
8	);

1	const { result, error } = await deepgram.listen.prerecorded.transcribeFile(
2	fs.readFileSync("./examples/spacewalk.wav"),
3	{
4	model: "nova-3",
5	}
6	);

1	const { result, error } = await deepgram.listen.prerecorded.transcribeFile(
2	fs.createReadStream("./examples/spacewalk.wav"),
3	{
4	model: "nova-3",
5	}
6	);

1	import { createClient } from "@deepgram/sdk";
2	import { webvtt } from "@deepgram/captions";
3	// - or -
4	// import { createClient, webvtt } from "@deepgram/sdk";
5
6	const deepgram = createClient("DEEPGRAM_API_KEY");
7
8	const { result, error } = await deepgram.listen.prerecorded.transcribeUrl(
9	{
10	url: "https://dpgr.am/spacewalk.wav"
11	},
12	{
13	model: "nova-3",
14	}
15	);
16
17	if (error) {
18	console.error(error);
19	}
20
21	const captions = webvtt(result);

1	import { createClient } from "@deepgram/sdk";
2	import { srt } from "@deepgram/captions";
3	// - or -
4	// import { createClient, webvtt } from "@deepgram/sdk";
5
6	const deepgram = createClient("DEEPGRAM_API_KEY");
7
8	const { result, error } = await deepgram.listen.prerecorded.transcribeUrl(
9	{
10	url: "https://dpgr.am/spacewalk.wav"
11	},
12	{
13	model: "nova-3",
14	}
15	);
16
17	if (error) {
18	console.error(error);
19	}
20
21	const captions = srt(result);