Verbara.Sdk.VoiceAi.Stt 2.2.1

.NET 10.0 This package targets .NET 10.0. The package is compatible with this framework or higher. 
dotnet add package Verbara.Sdk.VoiceAi.Stt --version 2.2.1
                    


                    

                
NuGet\Install-Package Verbara.Sdk.VoiceAi.Stt -Version 2.2.1
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="Verbara.Sdk.VoiceAi.Stt" Version="2.2.1" />
For projects that support PackageReference, copy this XML node into the project file to reference the package. 
<PackageVersion Include="Verbara.Sdk.VoiceAi.Stt" Version="2.2.1" />
                    


                            Directory.Packages.props
                        

                    

                
<PackageReference Include="Verbara.Sdk.VoiceAi.Stt" />
                    


                            Project file
For projects that support Central Package Management (CPM), copy this XML node into the solution Directory.Packages.props file to version the package. 
paket add Verbara.Sdk.VoiceAi.Stt --version 2.2.1
                    


                    

                
#r "nuget: Verbara.Sdk.VoiceAi.Stt, 2.2.1"
#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. 
#:package Verbara.Sdk.VoiceAi.Stt@2.2.1
#:package directive can be used in C# file-based apps starting in .NET 10 preview 4. Copy this into a .cs file before any lines of code to reference the package. 
#addin nuget:?package=Verbara.Sdk.VoiceAi.Stt&version=2.2.1
                    


                            Install as a Cake Addin
                        

                    

                
#tool nuget:?package=Verbara.Sdk.VoiceAi.Stt&version=2.2.1
                    


                            Install as a Cake Tool

Verbara.Sdk.VoiceAi.Stt

Speech-to-text providers for Verbara.Sdk.VoiceAi turn-based pipelines. 7 providers, each implementing ISpeechRecognizer from Verbara.Sdk.VoiceAi. Native AOT, zero reflection, hand-rolled HTTP/WebSocket clients (no vendor SDK dependencies). MIT licensed.

Providers

Provider Mode Notes
Deepgram Streaming WebSocket Nova-2 model. Production default. Lowest latency in the catalog (~150ms).
Whisper (local) Batch Self-hosted whisper.cpp / OpenAI Whisper API endpoint. Air-gapped option.
Azure Whisper Batch Azure OpenAI Whisper deployments. Same format as Whisper with Azure auth.
Google Speech Streaming gRPC over HTTP/2 Standard model. Multi-language support.
Cartesia (Ink-Whisper) Streaming WebSocket Newer entrant; competitive latency at lower cost.
AssemblyAI (Universal) Streaming WebSocket Universal-2 model with strong technical/code recognition.
Speechmatics Streaming WebSocket Enterprise-grade with fine-grained punctuation/casing.

All providers report metrics via the Verbara.Sdk.VoiceAi.Stt Meter (latency histogram, request counters, error counters tagged by provider name). Health checks (SttHealthCheck) auto-registered when the recognizer is added through DI.

Install

dotnet add package Verbara.Sdk.VoiceAi.Stt

You almost always want Verbara.Sdk.VoiceAi (the orchestration package) too:

dotnet add package Verbara.Sdk.VoiceAi

Quick start (Deepgram)

using Verbara.Sdk.VoiceAi.Stt.DependencyInjection;

services.AddDeepgramSpeechRecognizer(o =>
{
    o.ApiKey = configuration["Deepgram:ApiKey"]!;
    o.Model = "nova-2";
    o.Language = "en-US";
});

The recognizer is now resolvable as ISpeechRecognizer and registered with the VoiceAi pipeline. Connect AudioSocket on the Asterisk side and you have a streaming STT bridge.

Per-provider DI extensions

Each provider has its own Add*SpeechRecognizer extension (in Verbara.Sdk.VoiceAi.Stt.DependencyInjection):

services.AddDeepgramSpeechRecognizer(o => { ... });
services.AddWhisperSpeechRecognizer(o => { ... });
services.AddAzureWhisperSpeechRecognizer(o => { ... });
services.AddGoogleSpeechRecognizer(o => { ... });
services.AddCartesiaSpeechRecognizer(o => { ... });
services.AddAssemblyAiSpeechRecognizer(o => { ... });
services.AddSpeechmaticsSpeechRecognizer(o => { ... });

Examples

  • Examples/VoiceAiExample/ — Deepgram + ElevenLabs + echo handler (default end-to-end demo).
  • Examples/VoiceAiAssemblyAiExample/ — AssemblyAI Universal-2.
  • Examples/VoiceAiSpeechmaticsExample/ — Speechmatics enterprise STT.
  • Examples/VoiceAiCartesiaExample/ — Cartesia Ink-Whisper STT + Sonic-3 TTS.

Native AOT

All HTTP/WebSocket clients hand-rolled with HttpClient / ClientWebSocket. JSON serialization via source-generated JsonSerializerContext (VoiceAiSttJsonContext). 0 trim warnings. See ADR-0014 for the no-vendor-SDK rationale.

License

MIT. Part of the Verbara.Sdk project.

Product Compatible and additional computed target framework versions.
.NET net10.0 is compatible.  net10.0-android was computed.  net10.0-browser was computed.  net10.0-ios was computed.  net10.0-maccatalyst was computed.  net10.0-macos was computed.  net10.0-tvos was computed.  net10.0-windows was computed. 
Compatible target framework(s)
Included target framework(s) (in package)
Learn more about Target Frameworks and .NET Standard.

NuGet packages

This package is not used by any NuGet packages.

GitHub repositories

This package is not used by any popular GitHub repositories.

Version Downloads Last Updated
2.2.1 214 5/23/2026
2.2.0 120 5/20/2026
2.1.2 133 5/8/2026
2.1.1 98 5/7/2026
2.1.0 638 5/7/2026
2.0.0 98 5/6/2026