Deepgram .NET SDK

Official .NET SDK for Deepgram. Start building with our powerful transcription & speech understanding API.

This SDK only supports hosted usage of api.deepgram.com.

Getting an API Key

🔑 To access the Deepgram API you will need a free Deepgram API Key.

Documentation

Complete documentation of the .NET SDK can be found on the Deepgram Docs.

You can learn more about the full Deepgram API at https://developers.deepgram.com.

Installation

To install the C# client library using NuGet:

Run the following command from your terminal in your projects directory:

dotnet add package Deepgram

Targeted Frameworks

6.0.0
5.0.0
.NET Core 3.1
.NET Standard 2.0

Configuration

To setup the configuration of the Deepgram Client you can do one of the following:

Create a Deepgram Client instance and pass in credentials in the constructor.

var credentials = new Credentials(YOUR_DEEPGRAM_API_KEY);
var deepgramClient = new DeepgramClient(credentials);

Provide the Deepgram API key and optional API Url in appsettings.json:

{
  "appSettings": {
    "Deepgram.Api.Key": "YOUR_DEEPGRAM_API_KEY",
    "Deepgram.Api.Uri": "api.deepgram.com"
  }
}

Note: In the event multiple configuration files are found, the order of precedence is as follows:

* ```appsettings.json``` which overrides
* ```settings.json```

Access the Configuration instance and set the appropriate key in your code for example:

Configuration.Instance.Settings["appSettings:Deepgram.Api.Key"] = "YOUR_DEEPGRAM_API_KEY";
Configuration.Instance.Settings["appSettings:Deepgram.Api.Uri"] = "api.deepgram.com";

Examples

Sending a Remote File for Transcription

var credentials = new Credentials(DEEPGRAM_API_KEY);

var deepgramClient = new DeepgramClient(credentials);

var response = await deepgramClient.Transcription.Prerecorded.GetTranscriptionAsync(
    new Deepgram.Transcription.UrlSource("https://static.deepgram.com/examples/Bueller-Life-moves-pretty-fast.wav"),
    new Deepgram.Transcription.PrerecordedTranscriptionOptions()
    {
        Punctuate = true
    });

Sending a Local File for Transcription

var credentials = new Credentials(DEEPGRAM_API_KEY);

var deepgramClient = new DeepgramClient(credentials);

using (FileStream fs = File.OpenRead("path\\to\\file"))
{
    var response = await deepgramClient.Transcription.Prerecorded.GetTranscriptionAsync(
        new Deepgram.Transcription.StreamSource(
            fs,
            "audio/wav"),
        new Deepgram.Transcription.PrerecordedTranscriptionOptions()
        {
            Punctuate = true
        });
}

Real-time Transcription

The example below demonstrates sending a pre-recorded audio to simulate a real-time stream of audio. In a real application, this type of audio is better handled using the pre-recorded transcription.

var credentials = new Credentials(DEEPGRAM_API_KEY);

var deepgramClient = new DeepgramClient(credentials);

using (var deepgramLive = deepgramClient.CreateLiveTranscriptionClient())
{
    deepgramLive.ConnectionOpened += HandleConnectionOpened;
    deepgramLive.ConnectionClosed += HandleConnectionClosed;
    deepgramLive.ConnectionError += HandleConnectionError;
    deepgramLive.TranscriptReceived += HandleTranscriptReceived;

    // Connection opened so start sending audio.
    async void HandleConnectionOpened(object? sender, ConnectionOpenEventArgs e)
    {
        byte[] buffer;

        using (FileStream fs = File.OpenRead("path\\to\\file"))
        {
            buffer = new byte[fs.Length];
            fs.Read(buffer, 0, (int)fs.Length);
        }

        var chunks = buffer.Chunk(1000);

        foreach (var chunk in chunks)
        {
            deepgramLive.SendData(chunk);
            await Task.Delay(50);
        }

        await deepgramLive.FinishAsync();
    }

    void HandleTranscriptReceived(object? sender, TranscriptReceivedEventArgs e)
    {
        if (e.Transcript.IsFinal && e.Transcript.Channel.Alternatives.First().Transcript.Length > 0) {
            var transcript = e.Transcript;
            Console.WriteLine($"[Speaker: {transcript.Channel.Alternatives.First().Words.First().Speaker}] {transcript.Channel.Alternatives.First().Transcript}");
        }
    }

    void HandleConnectionClosed(object? sender, ConnectionClosedEventArgs e)
    {
        Console.Write("Connection Closed");
    }

    void HandleConnectionError(object? sender, ConnectionErrorEventArgs e)
    {
        Console.WriteLine(e.Exception.Message);
    }

    var options = new LiveTranscriptionOptions() { Punctuate = true, Diarize = true, Encoding = Deepgram.Common.AudioEncoding.Linear16 };
    await deepgramLive.StartConnectionAsync(options);

    while (deepgramLive.State() == WebSocketState.Open) { }
}

Logging

The Library uses Microsoft.Extensions.Logging to preform all of it's logging tasks. To configure logging for your app simply create a new ILoggerFactory and call the LogProvider.SetLogFactory() method to tell the Deepgram library how to log. For example, to log to the console with Serilog, you'd need to install the Serilog package with dotnet add package Serilog and then do the following:

using Microsoft.Extensions.Logging;
using Microsoft.Extensions.Configuration;
using Deepgram.Logger;
using Serilog;

var log = new LoggerConfiguration()
    .MinimumLevel.Debug()
    .WriteTo.Console(outputTemplate: "{Timestamp:HH:mm} [{Level}]: {Message}\n")
    .CreateLogger();
var factory = new LoggerFactory();
factory.AddSerilog(log);
LogProvider.SetLogFactory(factory);

Development and Contributing

Interested in contributing? We ❤️ pull requests!

To make sure our community is safe for all, be sure to review and agree to our Code of Conduct. Then see the Contribution guidelines for more information.

Getting Help

We love to hear from you so if you have questions, comments or find a bug in the project, let us know! You can either:

jkroll-deepgram/deepgram-dotnet-sdk