22 packages tagged with “transcription”
OpenAI C# / .NET library, using GPT-4, 3.5 and 3, DALL-E 3, DALL-E 2, Whisper, etc. It supports OpenAI and Azure-OpenAI APIs, dependency injections. Developed for public and free usage.
PlayFab Party is a set of cross-platform libraries and services for easily adding real-time networking and accessible chat communication to your multiplayer game. To use this package please enable Party in the PlayFab Game Manager.
PlayFab Party Helper Library for Xbox Live is a library designed to help games using PlayFab Party meet Xbox Requirements (XRs).
Use this extension to transcript any spanish text to Andaluh
Local speech-to-text transcription using Whisper models with ONNX Runtime. Zero-configuration, automatic GPU acceleration, and lazy model downloading.
This module contains 12 functions: Returns the change, the incoming text in a different language keyboard layout, for example engrus - from English into Russian And return transcription incoming text, symbols of another language, such as engrust - from English into Russian
A .NET client library for the CompactifAI API. Easily integrate AI chat completions, text completions, and audio transcription into your .NET applications.
AudioSummarizer - Forensic audio characterization library with speech-to-text and speaker analysis
Whisper-based audio transcription for ConsoleImage. Auto-generates subtitles from video/audio files using OpenAI Whisper models. Supports speaker diarization and multiple output formats (SRT, VTT).
Audio analysis plugin for DoomSummarizer. Speech-to-text transcription and speaker diarization.
Video analysis plugin for DoomSummarizer. Shot detection, scene segmentation, and transcription support.
This package provides the capability of subtitle transcription with Azure AI Speech.
Transcribe audio using Borg API for as little as $0.06 per hour.
A clean and minimalistic .NET client library for the FastWhisper speech-to-text API.
VideoScript - A powerful .NET tool for transcribing video and audio files to text using Apple Silicon GPU acceleration. Features: - Automatic video/audio detection and audio extraction via FFmpeg - GPU-accelerated transcription using MLX-Audio and Qwen3-ASR model - Support for multiple languages including Chinese and English - Automatic paragraph formatting based on sentence pauses - First-run automatic setup (FFmpeg, Python venv, model download) - ModelScope support for faster downloads in China Usage: videoscript input.mp4 # Transcribe video file videoscript input.mp3 -o output.txt # Specify output file videoscript input.wav --language zh # Specify language videoscript --help # Show help videoscript status # Check environment status videoscript models # List available models Requirements: - macOS with Apple Silicon (M1/M2/M3/M4) - .NET 8.0 Runtime - Python 3.10+ (auto-configured) - Homebrew (for FFmpeg auto-installation)
Our service converts your video/audio stream data into text and provides that information to you in a form of HTML widgets (iframe) or via programmatic Api. For On-demand media, we deliver WebVTT captions file that you can embed directly into your player.
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.
Generative AI library for .NET 10.0 with built-in OpenAI ChatGPT and Google Gemini API clients and support for C# function calling via reflection. Features: - Chat Completion - Response Streaming - Text Embedding - Text-to-Speech - Speech-to-Text - Moderation - Configurable Token Limit - Configurable Character Limit - Configurable Message Limit - Message Pinning - Function Calling - Support for Dependency Injection - Automatic Reattempt on Failure - Advanced Customization