MCP server that gives Claude, Cursor and other AI agents a voice: generate voiceovers, multi-speaker dialogue and SRT/VTT subtitles with the Miragea API.
Voxtral Mini Realtime speech-to-text in MLX
Speech-to-text for Flet apps via OS-native recognition (Android/iOS)
Local, offline Telegram & Instagram chat transcriber - voice & video via Whisper, screenshots via OCR, photos via a local vision model
Text-to-speech, speech-to-text, and realtime voice feature for Kestrel Sovereign agents
On-device Speech-to-Text & Neural Diarization framework for Android Termux (Whisper.cpp Vulkan GPU & Sherpa-ONNX)
Wayland hotkey dictation CLI and daemon with local or hosted transcription.
Official Python SDK for the Scriptivox transcription API: upload, transcribe, wait, export SRT/VTT/text, list, and verify webhooks.
Google Gemini API plugin for the cjm-transcription-plugin-system library - provides speech-to-text transcription with configurable model selection and parameter control.
Mistral Voxtral STT integration for Vision Agents
Local transcription of voicebot calls and phone recordings into timed speaker turns.
Local-first transcription tool for Korean meetings (audio file -> txt)
Standalone local WebSocket transcription (STT) server, client, and pluggable ASR backends for the Pipecat ecosystem
Python SDK for Speechall API - Speech-to-text transcription service
音视频转文字 CLI / MCP Server：阿里云百炼录音文件识别，支持说话人分离与微信语音 SILK
Local-first Audio Intelligence MCP server
OpenAI Whisper plugin for the cjm-transcription-plugin-system library - provides local speech-to-text transcription with configurable model selection and parameter control.
Fast GPT-3 client for Windows and Unix that supports both text and speech in any language.
Python client for streaming and offline speech-to-text
Cross-platform media transcription toolkit: URL or file in, timestamped transcripts and subtitle files out.
A versatile, plug-and-play Python AI toolkit for building offline intelligent assistants.
llama-index readers lokutor integration: transcribe audio into Documents with Lokutor speech-to-text
Official Gnani AI MCP server — Speech-to-Text, Text-to-Speech, and Voice Clone for Indian languages
Leopard speech-to-text engine demos
Offline-first diarized transcription: CLI and Python library
llama-index tools lokutor integration: give agents Lokutor text-to-speech and speech-to-text
A library for sending Sinhala audio files to a Flask API and decoding the received text
Push-to-talk speech-to-text input using OpenAI Whisper
GENSHI Voice STT SDK — high-accuracy domain-specific speech-to-text
Lokutor text-to-speech and speech-to-text components for Haystack
Shunyalabs ASR & TTS plugin for LiveKit Agents
This package is for extract text from audio/video file
Aavaaz — production-grade speech-to-text platform built on WhisperLive
Convert audio files to subtitles (VTT, SRT) using Faster-Whisper
Local push-to-talk dictation for macOS using Whisper large-v3-turbo on MLX
Professional Knowledge Hub - Capture, organize, and discover knowledge from videos, PDFs, and documents
AssemblyAI streaming STT integration for Vision Agents
Lightweight stdio MCP client that proxies conversion tool calls to a remote holy-moly-server deployment over HTTP
Speech-to-text CLI and system-tray app for dictating into any focused window. Local (vosk, faster-whisper) or cloud (groq, openai) backends, batch or streaming.
Official Python SDK for the Typeless External Transcript API
A Python developer toolkit with beautiful terminal output: debugging decorators (logging, timing, variable tracking), a thread-safe Logger with Grafana/Loki shipping, provider-agnostic email (SMTP/Resend/HTTP), streaming speech-to-text (Deepgram, AssemblyAI, Google, Azure, AWS, WhisperLive), and FastAPI request recorders.
MCP server for Whipscribe transcription. Beta service — endpoints and quotas may change; not suitable for production.
One interface to run and compare any speech-to-text model — local & cloud.
Personal voice assistant using OpenAI, g4f fallback providers, Google Cloud speech services, and local audio assets.
Google EMEA gTech Ads Data Science Team's solution to automatically translate and dub video ads into multiple languages using AI.
Aethex MCP Server
High-performance Whisper Speech Recognition Engine for Windows with C++ acceleration