Voxa.Speech.Mistral 0.7.2-alpha

.NET 10.0 This package targets .NET 10.0. The package is compatible with this framework or higher.
This is a prerelease version of Voxa.Speech.Mistral. 
dotnet add package Voxa.Speech.Mistral --version 0.7.2-alpha
                    


                    

                
NuGet\Install-Package Voxa.Speech.Mistral -Version 0.7.2-alpha
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="Voxa.Speech.Mistral" Version="0.7.2-alpha" />
For projects that support PackageReference, copy this XML node into the project file to reference the package. 
<PackageVersion Include="Voxa.Speech.Mistral" Version="0.7.2-alpha" />
                    


                            Directory.Packages.props
                        

                    

                
<PackageReference Include="Voxa.Speech.Mistral" />
                    


                            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 Voxa.Speech.Mistral --version 0.7.2-alpha
                    


                    

                
#r "nuget: Voxa.Speech.Mistral, 0.7.2-alpha"
#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 Voxa.Speech.Mistral@0.7.2-alpha
#: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=Voxa.Speech.Mistral&version=0.7.2-alpha&prerelease
                    


                            Install as a Cake Addin
                        

                    

                
#tool nuget:?package=Voxa.Speech.Mistral&version=0.7.2-alpha&prerelease
                    


                            Install as a Cake Tool

Voxa.Speech.Mistral

Mistral Voxtral TTS and STT engines for Voxa pipelines. Mistral's audio API is OpenAI-compatible: TTS at /v1/audio/speech, transcription at /v1/audio/transcriptions.

This is the remote (API, key-required) Voxtral tier. For a local, fully-offline privacy tier on the same model family, use Voxa.Speech.Voxtral (Voxtral-Mini-4B-Realtime via local vLLM) and switch with "Voxa:Stt": "Voxtral" vs "Mistral".

Install

dotnet add package Voxa.Speech.Mistral --prerelease

Quickstart

using Voxa.Speech;
using Voxa.Speech.Mistral;

var mistral = new MistralSpeechOptions
{
    ApiKey = "<your-mistral-key>",
    Model = "voxtral-tts",
    Voice = "alloy",
};

var pipeline = Pipeline.Build()
    .Source(...)
    .Then(new MicrosoftAgentsProcessor(yourAgent))
    .Then(Mistral.Synthesis(mistral))
    .Sink(...);

What's included

  • MistralTextToSpeechEngine — POSTs to /v1/audio/speech with response_format=pcm, streams the chunked response.
  • MistralSpeechToTextEngine — buffers the utterance and POSTs it to /v1/audio/transcriptions at speech-end. With SttStreaming (default true) it sends stream=true and surfaces the SSE response as interim transcription.text.delta partials followed by a transcription.done final; set it false for a single batched final. The API takes a complete clip, so audio is sent once per utterance (not incrementally).
  • MistralVoiceCatalog — list/clone voices via /v1/audio/voices.
  • MistralSpeechOptions — api key, base URL, model/voice, STT model/language/streaming, sample rates.
  • Mistral.Synthesis(...) — one-liner TTS processor factory.

Register both via the meta-package and pick per role: "Voxa:Tts": "Mistral" and/or "Voxa:Stt": "Mistral".

STT config keys

Key Default Notes
Voxa:Mistral:SttModel voxtral-mini-latest Transcription model id.
Voxa:Mistral:SttStreaming true Stream the SSE response (interims + final); false = one batched final.
Voxa:Mistral:SttLanguage null BCP-47 hint; null auto-detects.
Voxa:Mistral:InputSampleRate 16000 PCM rate the engine wraps as WAV before posting.
Voxa:Mistral:SttBufferSeconds 30 Safety-backstop flush if VAD never fires speech-end; 0 disables.

License

MIT.

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 (1)

Showing the top 1 NuGet packages that depend on Voxa.Speech.Mistral:

Package Downloads
Voxa

Batteries-included Voxa package. One package reference: AddVoxa(cfg) + MapVoxaVoice("/voice").UseDefaults() gives a working voice bot with STT, TTS, VAD, and an OpenAI chat agent — no knowledge of frames required.

GitHub repositories

This package is not used by any popular GitHub repositories.

Version Downloads Last Updated
0.7.2-alpha 89 7/10/2026
0.7.1-alpha 71 7/10/2026
0.7.0-alpha 80 7/10/2026
0.6.0-alpha 76 6/22/2026
0.5.0-alpha 80 6/13/2026
0.4.0-alpha 1,248 5/10/2026
0.3.0-alpha 77 5/9/2026
0.2.0-alpha 73 5/8/2026