speech-to-text-api 开源项目推荐（21 个）

rtzr /Awesome-Korean-Speech-Recognition

한국어 음성인식 STT API 리스트. 각 성능 벤치마크.

Evil0ctal /Fast-Powerful-Whisper-AI-Services-API

⚡ 一款用于自动语音识别 (ASR)、翻译的高性能异步 API。不需要购买Whisper API，使用本地运行的Whisper模型进行推理，并支持多GPU并发，针对分布式部署进行设计。还内置了包括TikTok、抖音等社交媒体平台的爬虫，可实现来自多个社交平台的无缝媒体处理，为媒体内容数据自动化处理提供了强大且可扩展的解决方案。

HenestrosaDev /audiotext

一个桌面应用程序，可以从文件、麦克风输入或YouTube视频中转录音频，并支持内容翻译和制作字幕。

StudiYash /DweshaMukt

DweshaMukt leverages BERT and deep learning to detect hate speech in Hinglish, Hindi, and English across text, audio, video, images, GIFs, and YouTube comments. With real-time analysis, emoticon detection, and a Streamlit interface, it aims to foster safer online spaces through advanced NLP techniques.

molanxuan-del /DSH-VoxPolish

「声琢」VoxPolish —— 把说出来的话打磨成清晰表达：原话/整理后双通道，先说、先改、再发送，全程不碰输入框。本地 SenseVoice 识别，无需额外下载模型。

NthnUlmr /DiscordLiveTranscriptionBot

A discord bot which transcribes your audio in real time using a combination of API calls to other services.

alhazenlabs /jarvis

该项目在 GitHub 上没有填写描述

ascender1729 /ClearSpeak

ClearSpeak is a real-time audio transcription application using Google's Speech-to-Text API. It features a Tkinter-based GUI, filtering background noise, and providing clear speech transcription.

MetKurdAI /metkurd-api

Official REST API V2 documentation, OpenAPI specification, Postman collection and examples for MetKurd AI.

ineed-coffee /seesun

🎁 세상을 밝혀주는 따듯한 서비스 시선 🎁 멀티캠퍼스 딥러닝 기반 AI엔지니어링 과정 파이널 프로젝트

vkop007 /-Speech-To-Text-Recognition-App

Speech To Text Recognition App converts spoken words to written text in real-time using the browser's speech recognition API. The app is built on React and provides users with easy control of speech recognition, manipulation of text, and copying to the clipboard. It is an accessible way to input text for users with disabilities.

ShouryaKapoor /RealTime_Transcripter_Mini_Project

Automated Transcription System is a Python-based app using OpenAI's Whisper model for real-time audio/video transcription. It features a GUI, monitors a folder for new media files, and supports multiple formats. The app ensures efficient processing, avoids duplicates, and provides logs, making it ideal for seamless speech-to-text conversion.

speechstack-ai /recipes

Open-source recipe collection powering speechstack.com

ilya-filatov-94 /Voice-assistent

Voice assistent for Desktop

ardamoustafa1 /ASR-Automatic-Speech-Recognition-

Advanced Cyber Speech Intelligence Platform powered by Faster-Whisper & NLP. Features real-time transcription, toxicity detection, speaker diarization, and batch processing.

sounak1125 /voxden

Open-source alternative to Superwhisper and Wispr Flow for Windows and Mac. Private, system-wide voice-to-text with local transcription. Free to use, with an optional paid Pro subscription.

fasuizu-br /brainiall-transcription-skill

Agent Skill for PT-BR and Spanish diarized transcription to JSON, SRT, and WebVTT

versevo-ai /versevo-ai

该项目在 GitHub 上没有填写描述

Speechall /speechall-swift-sdk

Swift SDK for the Speechall API - Single endpoint for every speech-to-text model

AndroidWithRossyn /AIVoiceTextTranslator-CodersSmile

该项目在 GitHub 上没有填写描述