Base Speech-to-Text service interface and implementation for converting speech to text.
Whisper-based ISpeechToTextClient implementation for ElBruno.Realtime. Provides local speech-to-text using Whisper.net with automatic GGML model download. Supports tiny.en (fast) and base.en (accurate) models.
Speech abstractions for Compendium Framework: ISpeechToText. Provider-agnostic interfaces for speech-to-text transcription (batch + streaming) across Whisper, Deepgram, and similar engines.
Audio transcription parser for FieldCure.DocumentParsers. Converts MP3, WAV, M4A, OGG, FLAC, and WebM audio into timestamped Markdown transcripts via Whisper.net.
Cross-platform Text-to-Speech and Speech-to-Text library for .NET MAUI and Android.
Pure C# (.NET 10) inference for NVIDIA Parakeet TDT speech recognition (FastConformer encoder + Token-and-Duration Transducer), loading the official .nemo checkpoint or the ONNX export, with no native dependencies.
Official C# SDK for the Speech Revolutions speech-to-text API
Official .NET SDK for the FalaAI API - AI-powered call transcription, diagnosis and compliance auditing.
Canned speech-to-text and text-to-speech clients for testing code built on CasCap.Api.Voice without a speech backend.
ForeverTools MCP Server — 13 AI tools: summarize, translate, sentiment, OCR, speech-to-text, text-to-speech, image generation, web fetch, keyword extraction, code explain, paraphrase, Markdown→HTML, JSON formatting to Claude Code and any MCP-compatible client. Bring your own AI/ML API key. Install as a .NET tool: dotnet tool install -g ForeverTools.Mcp
.NET native linux-arm64 wrapper for the sherpa-ncnn project. In general, you don't need to use this package directly. Please use https://www.nuget.org/packages/org.k2fsa.sherpa.ncnn instead
.NET native osx-arm64 wrapper for the sherpa-ncnn project. In general, you don't need to use this package directly. Please use https://www.nuget.org/packages/org.k2fsa.sherpa.ncnn instead
Local ASR transcript normalizer for .NET, wrapping superwhisper/s1-mini (0.6B Qwen3 fine-tune) via ONNX Runtime GenAI. Auto-downloads the INT4 ONNX model from HuggingFace and exposes a TranscriptNormalizer API plus IChatClient.
Refine a speech-to-text transcript with an injected chat model — glossary-guided corrections behind a sound-alike acceptance gate, timings kept by construction, every change reported with its original. Filer-unaware.
Core abstractions for speech-to-text with pluggable providers
A comprehensive .NET SDK for integrating with the ElevenLabs API. This SDK provides access to text-to-speech, voice management, speech-to-text, voice changing, and audio isolation features.
.NET process wrapper for invoking an independently installed OpenAI Whisper CLI executable from C# applications. The package builds command-line arguments and starts Whisper as a separate operating-system process; it does not include, distribute, install, download, link against, or license OpenAI Whisper, Whisper models, Python, PyTorch, CUDA, or GPU drivers.
Speech-to-Text for .NET using Whisper, powered by AI/ML API. Transcribe audio files, generate subtitles (SRT/VTT), detect languages, and get word-level timestamps. Supports MP3, WAV, M4A, WebM, and more. Perfect for meeting transcription, podcast subtitles, voice notes, and accessibility features.
SDK oficial de Sysmotor. Este producto es un SDK oficial desarrollado por Intrepid Vision. La funcionalidad principal es facilitar a los desarrolladores internos la integración de las APIs para el proceso denominado Speech to Text.
.NET native win-x86 wrapper for the sherpa-ncnn project. In general, you don't need to use this package directly. Please use https://www.nuget.org/packages/org.k2fsa.sherpa.ncnn instead
Vosk speech-to-text provider for VoiceToText
Resident CPU/CUDA Whisper speech transcription with host-owned model storage and lifetime.
Whisper.net speech-to-text provider for VoiceToText
NAudio-based microphone capture for VoiceToText (Windows)
Speech recognition for .NET. Managed transcription, timing and speaker recognition. Unaffiliated with other products or companies named OneSpeech.
Reusable Blazor components for ElBruno.Whisper speech-to-text experiences, including model selection, live transcript viewing, and file transcription workflows.
Speech recognition for .NET. Managed transcription, timing and speaker recognition. Unaffiliated with other products or companies named OneSpeech.
Speech recognition for .NET. Managed transcription, timing and speaker recognition. Unaffiliated with other products or companies named OneSpeech.
Speech recognition for .NET. Managed transcription, timing and speaker recognition. Unaffiliated with other products or companies named OneSpeech.
Speech recognition for .NET. Managed transcription, timing and speaker recognition. Unaffiliated with other products or companies named OneSpeech.
Speech recognition for .NET. Managed transcription, timing and speaker recognition. Unaffiliated with other products or companies named OneSpeech.
Shared speech-to-text contracts for the voice orchestration stack.
Linux (Wayland) voice typing with global hotkeys and OpenAI-compatible speech-to-text.
A clean and minimalistic .NET client library for the FastWhisper speech-to-text API.
Pulsa STT (Speech-to-Text) SDK for speech transcription
Context-aware voice insertion heuristics: filler-word stripping, sentence continuation detection, capitalisation and punctuation correction for speech-to-text input.
Idiomatic, async-first .NET client for the Fish Audio API: text-to-speech (buffered and streaming), realtime WebSocket TTS, speech-to-text, and voice-model management. Hand-crafted, MessagePack-correct, live-verified against the real API.
Windows STT wrapper package for the voice orchestration stack.
Linux STT wrapper package for the voice orchestration stack.
MAUI STT wrapper package for the voice orchestration stack.
Speech recognition for .NET. Managed transcription, timing and speaker recognition. Unaffiliated with other products or companies named OneSpeech.
Local speech-to-text transcription using Whisper models with ONNX Runtime. Zero-configuration, automatic GPU acceleration, and lazy model downloading.
ApifantTranscribe provides advanced audio transcription services with multiple specialized transcription methods - Full-text transcription for complete, accurate speech-to-text conversion - Diarization transcription for multi-speaker audio with speaker separation Perfect for applications requiring flexible speech recognition. Supports various audio formats (MP3, WAV) with a maximum file size of 40MB.
The .NET SDK for the MediSync API: speech to text, clinical notes and letters, ICD-10-GM coding, decisions and MediSync Connect.