Echo Scribe: Your API Key&Data

wean

About this app

Open Source & BYOK AI Assistant
EchoScribe summarizes audio, text, URLs, PDFs and shared messages using your own AI API keys or optional Local AI endpoints. No backend, no tracking, no ads, no subscriptions.

GitHub: https://github.com/vibecodingwean/echoscribe
Web App: https://app.wean.de/app
Info: https://app.wean.de
──────────────────────────────
Summary & Transcription
Record audio, share WhatsApp voice messages, paste text, or send URLs to EchoScribe. Choose OpenAI, Gemini, xAI Grok, or a Local AI Whisper-compatible endpoint for speech-to-text. Claude is supported for text summaries and translation.
──────────────────────────────
Realtime Speech
Enable OpenAI Realtime for live speech-to-text while recording, or choose a target language for live Realtime Translation. EchoScribe shows text as it arrives.
──────────────────────────────
Desktop Companions
Windows and Linux/GNOME companions add push-to-talk dictation, clipboard paste and browser summaries for Chrome, Edge, Brave, Chromium and Firefox through a local Native Messaging host. Downloads and setup are on GitHub and app.wean.de.
──────────────────────────────
Local AI PoC
Use your own Ollama-compatible /api/chat endpoint for summaries/translations and an OpenAI-compatible Whisper endpoint for STT. Defaults are qwen2.5:3b and whisper-1. Keep endpoints on a trusted LAN or VPN.
──────────────────────────────
Android Floating Dictation
Use EchoScribe as a movable system-wide dictation button in editable Android text fields. Dictate chat replies, turn rough speech into clean writing, or draft formal messages and letters without leaving the app you are typing in.

Recording starts only after you tap the floating microphone, the transcript is shown as a preview, and text is inserted only after you approve it.

This optional feature uses Android Accessibility only to detect editable fields, show the floating microphone button and insert approved text. Password, PIN, payment, banking, credit-card and phone fields are blocked.
──────────────────────────────
Privacy & Security
• No data is sent to EchoScribe servers because there are none.
• AI requests go directly from your device to the provider or Local AI endpoint you select.
• API keys are stored encrypted with Android Keystore.
• You control costs and limits in your provider dashboard.
• You are responsible for your own API keys, endpoints and usage costs.
──────────────────────────────
AI Image Generation
Create images from prompts from the Bubble Dock. Supports OpenAI, Gemini and Grok image models, with direct sharing and saving.
──────────────────────────────
Audio, TTS & Summaries
Record high-quality audio with live amplitude feedback, transcribe, summarize, translate, re-process, copy, share, or listen through supported TTS providers. History stays local on your device.
──────────────────────────────
Summarization Workflows
• Audio Summary: record, transcribe and summarize in one flow.
• Text Summary: paste or share text from other apps.
• URL Summary: extract webpage content locally before sending text to your chosen AI provider.
• Translation: change the target language and re-process the original source.
• Custom Prompts: adjust summary, URL, audio and dictation prompts.
──────────────────────────────
Provider Choice & Models
Standard/Fast presets include GPT-5.4-mini, Gemini 3.5 Flash, Claude 4.6 Sonnet, Grok 4.3 and Local AI qwen2.5:3b. Pro presets include GPT-5.5, Gemini 3.1 Pro, Claude 4.8 Opus and Grok 4.3 reasoning.
──────────────────────────────
API Key Setup
• OpenAI: platform.openai.com
• Gemini: aistudio.google.com
• Claude: console.anthropic.com
• Grok: console.x.ai
• Local AI: configure your own Ollama and Whisper URLs
──────────────────────────────
Simple & Transparent
One-time purchase. No subscriptions, no ads, no tracking. API costs are billed directly by your selected AI provider.

What’s new

Hotfix for Local AI preflight checks.
Local AI Whisper and Ollama availability are now checked with fast reachability endpoints before recording instead of running a full test transcription or chat completion.
The Android microphone flow now shows immediate progress log lines while checking Local AI and starts recording as soon as the checks pass.
Floating Dictation uses the same fast Local AI preflight path.