stt

telegram bot for self-hosted local inference of stable diffusion, text-to-speech and large language models, such as llama3

Evaluate results from ASR/Speech-to-Text quickly

AI writing assistant with voiced narrator and characters and an illustrator

Multimodal generative AI resources : talking heads, STT, TTS, image & video generation, and AI Agent

Data Curation Tool is a local-first dataset curation, tagging, model-management, downloader, 3D generation, media metadata, and tool-orchestration application. The current documentation set is stored in docs/wiki/

Training scripts for Speech-To-Text models for Ukrainian language

real time japanese speech recognition translator using wav2vec2

Run Vision LLMs, TTS and STT APIs. Website and API for https://text-generator.io

OpenAI Whisper in Home Assistant via the OpenAI API for use in the Assist pipeline

Microsoft Bing Speech API client in node.js

Open-source macOS menu bar app for voice-to-text dictation. Private, offline, multilingual speech recognition powered by Parakeet/whisper.cpp — auto-pastes transcriptions into the active app.

A simple matrix bot that transcribes your voice to text message

Offline Speech-to-Text (STT) service using Mistral's Voxtral model with Wyoming protocol compatibility for Home Assistant Assist integration.

Vosk4Unity is a module for the Unity Engine that provides a simple way to integrate speech recognition into your application. It is based on and powered by the Vosk speech recognition engine.

A lightweight library for normalizing speech transcripts before computing WER

speech to text gui for different (e.g. Whisper, Voxtral) models and backends, including whisper.cpp, crispasar, mlx-whisper, faster-whisper, ctranslate2; applies pyannote for diarization

Effortless Push-to-Talk Transcription, Anywhere.

🐍📦 Ultra-fast Python package for calculating and analyzing the Word Error Rate (WER). Built for the scalable evaluation of speech and transcription accuracy.

PAFTS : Library That Preprocessing Audio For TTS.

kospeech를 활용한 한국어 음성 인식 모델 개발