Deepgram 3.4.2

dotnet add package Deepgram --version 3.4.2
NuGet\Install-Package Deepgram -Version 3.4.2
This command is intended to be used within the Package Manager Console in Visual Studio, as it uses the NuGet module's version of Install-Package.
<PackageReference Include="Deepgram" Version="3.4.2" />
For projects that support PackageReference, copy this XML node into the project file to reference the package.
paket add Deepgram --version 3.4.2
#r "nuget: Deepgram, 3.4.2"
#r directive can be used in F# Interactive and Polyglot Notebooks. Copy this into the interactive tool or source code of the script to reference the package.
// Install Deepgram as a Cake Addin
#addin nuget:?package=Deepgram&version=3.4.2

// Install Deepgram as a Cake Tool
#tool nuget:?package=Deepgram&version=3.4.2

Deepgram .NET SDK

Nuget Build Status Contributor Covenant

Official .NET SDK for Deepgram. Power your apps with world-class speech and Language AI models.

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# SDK using NuGet:

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

dotnet add package Deepgram

Or use the Nuget package Manager.

Right click on project and select manage nuget packages

Targeted Frameworks

  • 7.0.x
  • 6.0.x

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);

Transcription

Remote Files

using Deepgram.Models;

var credentials = new Credentials(DEEPGRAM_API_KEY);

var deepgramClient = new DeepgramClient(credentials);

var response = await deepgramClient.Transcription.Prerecorded.GetTranscriptionAsync(
    new UrlSource("https://static.deepgram.com/examples/Bueller-Life-moves-pretty-fast.wav"),
    new PrerecordedTranscriptionOptions()
    {
        Punctuate = true
    });
UrlSource
Property Value Description
Url string Url of the file to transcribe

Local files

using Deepgram.Models;

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 StreamSource(
            fs,
            "audio/wav"),
        new PrerecordedTranscriptionOptions()
        {
            Punctuate = true
        });
}
StreamSource
Property Value Type reason for
Stream Stream stream to transcribe
MimeType string MIMETYPE of stream
PrerecordedTranscriptionOptions
Property Value Type reason for Possible values
Model string AI model used to process submitted audio
Version string Version of the model to use
Language string BCP-47 language tag that hints at the primary spoken language
Tier string Level of model you would like to use in your request
Punctuate bool Indicates whether to add punctuation and capitalization to the transcript
ProfanityFilter bool Indicates whether to remove profanity from the transcript
Redaction string[] Indicates whether to redact sensitive information pci, numbers, ssn
Diarize bool Indicates whether to recognize speaker changes
DiarizationVersion string Indicates which version of the diarizer to use
NamedEntityRecognition bool Indicates whether to recognize alphanumeric strings. obselete deprecated
MultiChannel bool Indicates whether to transcribe each audio channel independently
Alternatives int Maximum number of transcript alternatives to return
Numerals bool Indicates whether to convert numbers from written format
Numbers bool Indicates whether to convert numbers from written format
NumbersSpaces bool Indicates whether to add spaces between spoken numbers
Dates bool Indicates whether to convert dates from written format
DateFormat string Indicates the format to use for dates
Times bool Indicates whether to convert times from written format
Dictation bool Option to format punctuated commands
Measurements bool Option to convert measurments to numerical format
SmartFormat bool Indicates whether to use Smart Format on the transcript
SearchTerms string[] Terms or phrases to search for in the submitted audio
Replace string[] Terms or phrases to search for in the submitted audio and replace
Callback string Callback URL to provide if you would like your submitted audio to be processed asynchronously
Keywords string[] Keywords to which the model should pay particular attention to boosting or suppressing to help it understand context
KeywordBoost string Support for out-of-vocabulary
Utterances bool Indicates whether Deepgram will segment speech into meaningful semantic units
DetectLanguage bool Indicates whether to detect the language of the provided audio
Paragraphs bool Indicates whether Deepgram will split audio into paragraphs
UtteranceSplit decimal Length of time in seconds of silence between words that Deepgram will use when determining
Summarize object Indicates whether Deepgram should provide summarizations of sections of the provided audio
DetectEntities bool Indicates whether Deepgram should detect entities within the provided audio
Translate string[] anguage codes to which transcripts should be translated to
DetectTopics bool Indicates whether Deepgram should detect topics within the provided audio
AnalyzeSentiment bool Indicates whether Deepgram will identify sentiment in the transcript
Sentiment bool Indicates whether Deepgram will identify sentiment in the audio
SentimentThreshold decimal Indicates the confidence requirement for non-neutral sentiment

Generating Captions

var preRecordedTranscription =  await deepgramClient.Transcription.Prerecorded.GetTranscriptionAsync(streamSource,prerecordedtranscriptionOptions);
var WebVTT = preRecordedTranscription.ToWebVTT();
var SRT =  preRecordedTranscription.ToSRT();

Live Audio

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.

using Deepgram.CustomEventArgs;
using Deepgram.Models;
using System.Net.WebSockets;

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) { }
}
LiveTranscriptionOptions
Property Type Description Possible values
Model string AI model used to process submitted audio
Version string Version of the model to use
Language string BCP-47 language tag that hints at the primary spoken language
Tier string Level of model you would like to use in your request
Punctuate bool Indicates whether to add punctuation and capitalization to the transcript
ProfanityFilter bool Indicates whether to remove profanity from the transcript
Redaction string[] Indicates whether to redact sensitive information pci, numbers, ssn
Diarize bool Indicates whether to recognize speaker changes
DiarizationVersion string Indicates which version of the diarizer to use
NamedEntityRecognition bool Indicates whether to recognize alphanumeric strings. obselete deprecated
MultiChannel bool Indicates whether to transcribe each audio channel independently
Alternatives int Maximum number of transcript alternatives to return
Numerals bool Indicates whether to convert numbers from written format
Numbers bool Indicates whether to convert numbers from written format
NumbersSpaces bool Indicates whether to add spaces between spoken numbers
Dates bool Indicates whether to convert dates from written format
DateFormat string Indicates the format to use for dates
Times bool Indicates whether to convert times from written format
Dictation bool Option to format punctuated commands
Measurements bool Option to convert measurments to numerical format
SmartFormat bool Indicates whether to use Smart Format on the transcript
SearchTerms string[] Terms or phrases to search for in the submitted audio
Replace string[] Terms or phrases to search for in the submitted audio and replace
Callback string Callback URL to provide if you would like your submitted audio to be processed asynchronously
Keywords string[] Keywords to which the model should pay particular attention to boosting or suppressing to help it understand context
KeywordBoost string Support for out-of-vocabulary
Utterances bool Indicates whether Deepgram will segment speech into meaningful semantic units
DetectLanguage bool Indicates whether to detect the language of the provided audio
Paragraphs bool Indicates whether Deepgram will split audio into paragraphs
InterimResults bool Indicates whether the streaming endpoint should send you updates to its transcription as more audio becomes available
EndPointing string Indicates whether Deepgram will detect whether a speaker has finished speaking
VADTurnOff int Length of time in milliseconds of silence that voice activation detection (VAD) will use to detect that a speaker has finished speaking
Encoding string Expected encoding of the submitted streaming audio
Channels int Number of independent audio channels contained in submitted streaming audio
SampleRate int Sample rate of submitted streaming audio. Required (and only read) when a value is provided for encoding

Projects

projectId and memberId are of type string

Get Projects

Returns all projects accessible by the API key.

var result = await deepgramClient.Projects.ListProjectsAsync();

See our API reference for more info.

Get Project

Retrieves a specific project based on the provided projectId.

var result = await deepgramClient.Projects.GetProjectAsync(projectId);

See our API reference for more info.

Update Project

Update a project.

var project = new Project()
{
    Project = "projectId string",
    Name = "New name for Project"
}
var result = await deepgramClient.Projects.UpdateProjectAsync(project);

Project Type

Property Name Type Description
Id string Unique identifier of the Deepgram project
Name string Name of the project
Company string Name of the company associated with the Deepgram project

See our API reference for more info.

Delete Project

Delete a project.

var result = await deepgramClient.Projects.DeleteProjectAsync(projectId);

See our API reference for more info.

Keys

projectId,keyId and comment are of typestring

List Keys

Retrieves all keys associated with the provided project_id.

var result = await deepgramClient.Keys.ListKeysAsync(projectId);

See our API reference for more info.

Get Key

Retrieves a specific key associated with the provided project_id.

var result = await deepgramClient.Keys.GetKeyAsync(projectId,keyId);

See our API reference for more info.

Create Key

Creates an API key with the provided scopes.

var scopes = new string[]{"admin","member"};
var result = await deepgramClient.Keys.CreateKeyAsync(projectId,comment,scopes);

See our API reference for more info.

Delete Key

Deletes a specific key associated with the provided project_id.

var result = await deepgramClient.Keys.DeleteKeyAsync(projectId, keyId);

See our API reference for more info.

Members

projectId and memberId are of typestring

Get Members

Retrieves account objects for all of the accounts in the specified project_id.

var result = await deepgramClient.Projects.GetMembersScopesAsync(projectId,memberId);

See our API reference for more info.

Remove Member

Removes member account for specified member_id.

var result = await deepgramClient.Projects.RemoveMemberAsync(projectId,memberId);

See our API reference for more info.

Scopes

projectId and memberId are of typestring

Get Member Scopes

Retrieves scopes of the specified member in the specified project.

var result = await deepgramClient.Keys. GetMemberScopesAsync(projectId,memberId);

See our API reference for more info.

Update Scope

Updates the scope for the specified member in the specified project.

var scopeOptions = new UpdateScopeOption(){Scope = "admin"};
var result = await deepgramClient.Keys.UpdateScopeAsync(projectId,memberId,scopeOptions);

See our API reference for more info.

Invitations

List Invites

Retrieves all invitations associated with the provided project_id.

to be implmented

See our API reference for more info.

Send Invite

Sends an invitation to the provided email address.

to be implmentented

See our API reference for more info.

Delete Invite

Removes the specified invitation from the project.

to be implemented

See our API reference for more info.

Leave Project

Removes the authenticated user from the project.

var result = await deepgramClient.Projects.LeaveProjectAsync(projectId);

See our API reference for more info.

Usage

projectId and requestId typestring

Get All Requests

Retrieves all requests associated with the provided projectId based on the provided options.

var listAllRequestOptions = new listAllRequestOptions()
{
     StartDateTime = DateTime.Now
};
var result = await deepgramClient.Usage.ListAllRequestsAsync(projectId,listAllRequestOptions);
ListAllRequestOptions
Property Type Description
StartDateTime DateTime Start date of the requested date range
EndDateTime DateTime End date of the requested date range
Limit int number of results per page

See our API reference for more info.

Get Request

Retrieves a specific request associated with the provided projectId.

var result = await deepgramClient.Usage.GetUsageRequestAsync(projectId,requestId);

See our API reference for more info.

Summarize Usage

Retrieves usage associated with the provided project_id based on the provided options.

var getUsageSummmaryOptions = new GetUsageSummmaryOptions()
{
    StartDateTime = DateTime.Now
}
var result = await deepgramClient.Usage.GetUsageSummaryAsync(projectId,getUsageSummmaryOptions);
GetUsageSummaryOptions
Property Value Description
StartDateTime DateTime Start date of the requested date range
EndDateTime DateTime End date of the requested date range
Limit int number of results per page

See our API reference for more info.

Get Fields

Lists the features, models, tags, languages, and processing method used for requests in the specified project.

var getUsageFieldsOptions = new getUsageFieldsOptions()
{
    StartDateTime = Datetime.Now
}
var result = await deepgramClient.Usage.GetUsageFieldsAsync(projectId,getUsageFieldsOptions);
GetUsageFieldsOptions
Property Value Description
StartDateTime DateTime Start date of the requested date range
EndDateTime DateTime End date of the requested date range

See our API reference for more info.

Logging

The Library uses Microsoft.Extensions.Logging to preform all of its 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.

Testing

The test suite is located within Deepgram.Tests/. Run all tests with the following command from the top-level repository:

dotnet test

Upon completion, a summary is printed:

Passed!  - Failed:     0, Passed:    69, Skipped:     0, Total:    69, Duration: 906 ms - Deepgram.Tests.dll (net7.0)

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:

Product Compatible and additional computed target framework versions.
.NET net5.0 was computed.  net5.0-windows was computed.  net6.0 is compatible.  net6.0-android was computed.  net6.0-ios was computed.  net6.0-maccatalyst was computed.  net6.0-macos was computed.  net6.0-tvos was computed.  net6.0-windows was computed.  net7.0 is compatible.  net7.0-android was computed.  net7.0-ios was computed.  net7.0-maccatalyst was computed.  net7.0-macos was computed.  net7.0-tvos was computed.  net7.0-windows was computed.  net8.0 was computed.  net8.0-android was computed.  net8.0-browser was computed.  net8.0-ios was computed.  net8.0-maccatalyst was computed.  net8.0-macos was computed.  net8.0-tvos was computed.  net8.0-windows was computed. 
.NET Core netcoreapp2.0 was computed.  netcoreapp2.1 was computed.  netcoreapp2.2 was computed.  netcoreapp3.0 was computed.  netcoreapp3.1 was computed. 
.NET Standard netstandard2.0 is compatible.  netstandard2.1 was computed. 
.NET Framework net461 was computed.  net462 was computed.  net463 was computed.  net47 was computed.  net471 was computed.  net472 was computed.  net48 was computed.  net481 was computed. 
MonoAndroid monoandroid was computed. 
MonoMac monomac was computed. 
MonoTouch monotouch was computed. 
Tizen tizen40 was computed.  tizen60 was computed. 
Xamarin.iOS xamarinios was computed. 
Xamarin.Mac xamarinmac was computed. 
Xamarin.TVOS xamarintvos was computed. 
Xamarin.WatchOS xamarinwatchos was computed. 
Compatible target framework(s)
Included target framework(s) (in package)
Learn more about Target Frameworks and .NET Standard.

NuGet packages (2)

Showing the top 2 NuGet packages that depend on Deepgram:

Package Downloads
Fsel.Core

Fsel Core Package

fAI

Fred's experimentation with AI

GitHub repositories (1)

Showing the top 1 popular GitHub repositories that depend on Deepgram:

Repository Stars
VRCWizard/TTS-Voice-Wizard
Speech to Text to Speech. Song now playing. Sends text as OSC messages to VRChat to display on avatar. (STTTS) (Speech to TTS) (VRC STT System) (VTuber TTS)
Version Downloads Last updated
3.4.2 659 3/29/2024
3.4.1 3,895 2/13/2024
3.4.0 19,020 9/26/2023
3.3.0 1,250 9/14/2023
3.2.0 634 8/28/2023
3.1.0 1,936 8/14/2023
2.2.0 7,284 7/20/2023
2.1.0 2,924 6/30/2023
2.0.0 6,678 4/12/2023
1.13.0 1,293 1/17/2023
1.12.0 757 12/13/2022
1.11.1 551 11/30/2022
1.10.0 2,231 11/15/2022
1.9.0 821 10/30/2022
1.8.0 688 10/6/2022
1.7.1 667 10/1/2022
1.7.0 656 9/27/2022
1.6.0 660 9/20/2022
1.5.1 681 9/2/2022
1.4.1 702 8/17/2022
1.4.0 722 7/14/2022
1.3.1 688 7/1/2022
1.2.0 779 4/20/2022
1.1.0 1,004 2/4/2022
1.0.0 537 12/20/2021
1.0.0-beta2 564 11/22/2021
1.0.0-beta1 638 11/21/2021