🎙️ Transcribe podcast episodes quickly by pasting links and API keys, generating human-readable transcripts with timestamps for easy editing.

🎙️ Open Source AI Dictation App ⚡ Type 3x faster, no keyboard needed.

Privacy-first and free Speech-to-Text

A portal that offers a transcription chain for multi upload and processing of audio files using ASR, OCTRA, MAUS and EMU-webApp.

Official JavaScript SDK for Deepgram.

The AssemblyAI JavaScript SDK provides an easy-to-use interface for interacting with the AssemblyAI API, which supports async and real-time transcription, audio intelligence models, as well as the latest LeMUR models.

Notera turns audio into insights. 🎙️✨ Record or upload audio, get real-time transcriptions, AI-powered summaries, action items, and searchable transcripts—all wrapped in a sleek web + desktop app.

A cross-platform real-time subtitle display software. 一个跨平台的实时字幕显示软件。

This is a modern translation application powered by the Google Gemini API. It provides a clean, mobile-first user interface for fast and accurate text, voice, and image translation between multiple languages, and supports both online and offline modes.

Obsidian plugin to create high-quality transcriptions from markdown linked audio files

AI Tool 平台是一款一站式 AI 能力工具集，集成了以下六大核心模块： Prompt：Prompt 管理、生成与调试 知识库：知识库管理与文件管理 模型微调：微调任务管理与数据集管理 语音：ASR、TTS 与实时语音交互 图片：AI 图片生成 实用 Agent：视频、图片、文件、代码与自定义接口测试等多场景 Agent 平台基于 Next.js、TypeScript 和 Tailwind CSS 构建，并集成了 Casdoor 认证与 PostgreSQL 数据存储，为开发者和产品团队提供高效、可扩展的 AI 能力支撑。

Call Center，Contact Center，呼叫中心，客服系统，工单系统，智能外呼，大模型呼叫中心，智能呼叫中心

This is an n8n community node. It lets you use ai-coustics in your n8n workflows.

Really easy-to-use Typescript client for FunASR runtime server.

Deepgram Conversational AI demo

Praises is a text-to-speech tool that can help you read text easily.

self-hosted whisper webui

An audio labeling studio for ASR tasks (transcription, diarization, VAD, etc)

An AI chat app with TTS, STT and MCP support

Doctor management app