ion

All web apps in the Catalogue

ASR Studio

by yeahhe365 · io.github.yeahhe365.asr-studio

Not TrustedWeb appUnrated★ 277 stars

Multi-provider ASR web studio (Qwen, Doubao, Gemini, NIM, OpenAI-compatible &…

Multi-provider ASR web studio (Qwen, Doubao, Gemini, NIM, OpenAI-compatible & more) with recording, batch queue, PWA, local cache, and benchmarks.

Screenshots

  • Screenshot 1 of ASR Studio
  • Screenshot 2 of ASR Studio

About

一个功能丰富的网页应用,旨在为 Qwen、豆包、Gemini、NVIDIA NIM 以及 OpenAI、Groq、Deepgram、AssemblyAI、ElevenLabs、Mistral、Fireworks 等主流 ASR / 多模态语音模型提供一个强大、高效且用户友好的操作界面。无论您是需要转录会议记录、整理语音内容,还是进行任何形式的语音转文本工作,本工具都能为您提供流畅的体验。 - 多种音频输入方式: - 文件上传: 支持拖拽或点击选择多种常见音频格式(WAV, MP3, FLAC, M4A 等)。 - 批量队列: 可一次选择多个音频,逐个识别并显示每个文件的处理状态。 - 实时录音: 直接从麦克风录制音频,并带有实时音波可视化效果。 - 远程 URL: 豆包录音文件识别标准版 2.0 支持公网音频 URL;其他 Provider 会提示改用本地文件。 - 高效的转录核心: - 多厂商 ASR 驱动: 支持 Qwen 官方 ASR API、豆包录音文件识别标准版 2.0、Gemini 音频理解接口、NVIDIA NIM,以及主流模型库(OpenAI GPT-4o/Whisper、Groq Whisper、Deepgram Nova-3、AssemblyAI Universal、ElevenLabs Scribe、Mistral Voxtral、Fireworks Whisper)。 - 上下文提示: 可通过提供特定术语、人名或专业词汇作为上下文,显著提升识别的准确率。 - 多语言支持: 支持中文、英语、日语等多种语言的识别,并能自动检测语种。 - 反向文本标准化 (ITN): 可选功能,能将“一月五号”这样的口语化表达转换为“1月5日”等书面形式。 ASR Studio is the open-source project yeahhe365/ASR-Studio (https://github.com/yeahhe365/ASR-Studio) by yeahhe365, released under MIT. Ion packages it unmodified from commit 0b1e4995b96f, adding only a manifest, an icon and a storage compatibility script.

Source

Written by yeahhe365, published to Oikou by Ben Grande.

  • ★ 277 stars on GitHub
  • Licence: MIT
  • Upstream version v1.3.0
  • Built from commit 0b1e4995b96f

View the repository on GitHub

Age rating

Not rated. Nobody has said who this app is suitable for, so Personal Clouds and the Oikou app treat it as 18+.

What version 1.3.0 may do

Internet

It asks to reach these hosts, and no others:

  • dashscope.aliyuncs.com
  • openspeech.bytedance.com
  • api.assemblyai.com
  • api.deepgram.com
  • api.elevenlabs.io
  • api.fireworks.ai
  • api.groq.com
  • api.mistral.ai
  • api.openai.com
  • generativelanguage.googleapis.com
  • huggingface.co

Your camera, microphone and screen

  • Can use your microphone while you have it open

You choose which of these it gets, and your browser still asks you before each use.

Personal Cloud tools

  • Keep a database of its own on your Personal Cloud ion.db
  • Keep files in its own storage on your Personal Cloud ion.files

Notifications

It does not send push notifications.

Storage

Up to 1 GB on your Personal Cloud.

Add to Personal Cloud

Sign in to add this web app to a Personal Cloud of yours. It runs there, on your own computer, and you open it from there; nothing is installed on your phone.

Sign in to add

Versions

1.3.0 Latest Shown above

Published · a ready-built bundle

Imported from yeahhe365/ASR-Studio at 0b1e4995b96f (v1.3.0).

Report this app