Stenographer vs Google AI Edge Gallery

Your conversations are valuable. They should also stay private. Stenographer records, transcribes, identifies speakers, summarizes, and organizes audio directly on your iPhone or iPad. Capture from your phone or Apple Watch, then turn hours of audio into a readable, searchable record without sending your conversations to a transcription service. NEW IN STENOGRAPHER 2.0 • Seamless Transcript Read recordings as one continuous, newspaper-like conversation. Stenographer hides file splits and processing chunks while preserving the original audio behind every turn. • Know who said what Private, on-device speaker diarization separates conversations into natural speaker turns. Name a speaker and Stenographer can use an on-device voice profile to recognize that person in other recordings when there’s a confident match. • Private AI summaries On supported devices, summaries and labels use Apple’s on-device Foundation Models. An optional downloadable local fallback is available, and your transcripts remain on your device. • Record from your wrist Start recording from Apple Watch when reaching for your phone would interrupt the moment. Finished recordings remain queued on Apple Watch and retry until iPhone safely receives them for private transcription and analysis. MORE WAYS TO WORK • Continue recording in the background from iPhone or Apple Watch • Import existing audio files • Automatically detect supported languages • Transcribe speech or translate supported languages into English • Search across transcripts, summaries, and labels • Add labels and optional timestamps • Select exact transcript turns to share • Merge recordings and export all transcripts as JSON • Customize transcript fonts, speaker display, processing concurrency, and recording limits • Return to the classic per-recording layout at any time PRIVATE BY DESIGN Transcription, speaker identification, summaries, and labels run on your device whenever available. Nothing is uploaded unless you explicitly choose to share it. Speaker and optional fallback models may download when needed; your audio and transcripts are not uploaded for processing. ONE PURCHASE. NO SUBSCRIPTION. Record and transcribe without monthly fees, usage quotas, or cloud transcription charges. Ideal for meetings, lectures, interviews, research, personal notes, and private lifelogging. App icon designed by aaatelier.ch.

AI Edge Gallery is the premier destination for running the world’s most powerful open-source Large Language Models (LLMs) on your mobile device. Experience high-performance Generative AI directly on your hardware—fully offline, private, and lightning-fast. Now Featuring: EmbeddingGemma 2 This update brings official support for the newly released EmbeddingGemma 2 model. With this release, we bring cutting edge, multimodal semantic search running 100% on your device. Try out these new capabilities in our new features Instant Media Search and Video Moment Finder. Core Features - Agent Skills: Transform your LLM from a conversationalist into a proactive assistant. Use the Agent Skills tile to augment model capabilities with tools like Wikipedia for fact-grounding, interactive maps, and rich visual summary cards. You can even load modular skills from a URL or browse community contributions on GitHub Discussions. - AI Chat with Thinking Mode: Engage in fluid, multi-turn conversations and toggle the new Thinking Mode to peek "under the hood." This feature allows you to see the model’s step-by-step reasoning process, which is perfect for understanding complex problem-solving. Note: Thinking Mode currently works with supported models, starting with the Gemma 4 family. - Instant Media Search: Explore your photo library (or built-in sample media) with fast, search-as-you-type natural language queries and image-to-image similarity matching—with zero cloud roundtrips. - Video Moment Finder: Pinpoint exact moments inside videos using natural language descriptions. Jump straight to highlighted timestamps on an interactive timeline, trim clips, and save or export your favorite moments - Ask Image: Use multimodal power to identify objects, solve visual puzzles, or get detailed descriptions using your device’s camera or photo gallery. - Audio Scribe: Transcribe and translate voice recordings into text in real-time using high-efficiency on-device language models. - Prompt Lab: A dedicated workspace to test different prompts and single-turn use cases with granular control over model parameters like temperature and top-k. - Mobile Actions: Unlock offline device controls and automated tasks powered entirely by a finetune of FuntionGemma 270m. - Tiny Garden: A fun, experimental mini-game that uses natural language to plant and harvest a virtual garden using a finetune of FunctionGemma 270m. - Model Management & Benchmark: Gallery is a flexible sandbox for a wide variety of open-source models. Easily download models from the list or load your own custom models. Manage your model library effortlessly and run benchmark tests to understand exactly how each model performs on your specific hardware. - 100% On-Device Privacy: All model inferences happen directly on your device hardware. No internet is required, ensuring total privacy for your prompts, images, and sensitive data. Built for the Community AI Edge Gallery is an open-source project designed for the developer community and AI enthusiasts alike. Explore our example features, contribute your own skills, and help shape the future of the on-device agent ecosystem. Check out the source code on GitHub: https://github.com/google-ai-edge/gallery Note: This app is in active development. Performance is dependent on your device's hardware (CPU/GPU). For support or feedback, contact us at google-ai-edge-gallery-android-feedback@google.com.