Sono: Offline AI Notetaker

Never take notes again. Sono is an on-device AI transcription and summarization app. Whether you need to transcribe meetings, lectures, videos, and more, Sono takes notes for you so you can save time and focus on the discussion. Upload voice notes, audio files, or videos, and Sono will automatically convert speech to text. Sono also supports smart AI summaries and AI chat so you can ask questions, request rewrites, and generate action items. KEY FEATURES: • Unlimited transcription for audio and video in 99 languages • Transcribe voice notes, real-time audio, and video/audio files • Choose between five different transcription models • AI summaries and chat • Organize recordings in collections • Search transcripts • Copy and share transcripts (TXT, PDF, MD, DOCX, SRT) • Export recordings PRIVACY: • We do not collect any user data. Both transcription and AI features run 100% locally, so your data never leaves your device FAQ: What is the longest transcription supported? We support regular transcription of voice notes, audio files, and video files up to 8 hours long. We support live transcription up to 2 hours long. You can transcribe as many recordings as you would like. Is the app actually fully local? Yes! The app uses local models of OpenAI's Whisper, NVIDIA's Parakeet, and Meta AI's Llama, so all transcription and AI features work on-device. A network connection is only required once to download each transcription or AI model. Your data never leaves your device unless you choose to share it. As we do not want to upload your data to the cloud, your transcriptions will be deleted if you delete the application. We recommend backing up important transcriptions. What languages are supported? Transcription is available in: Afrikaans, Albanian, Amharic, Arabic, Armenian, Assamese, Azerbaijani, Bashkir, Belarusian, Bengali, Bosnian, Breton, Bulgarian, Burmese, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Faroese, Finnish, French, Galician, Georgian, German, Greek, Gujarati, Haitian Creole, Hausa, Hawaiian, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Javanese, Kannada, Kazakh, Khmer, Korean, Lao, Latin, Latvian, Lingala, Lithuanian, Luxembourgish, Macedonian, Malagasy, Malay, Malayalam, Maltese, Māori, Marathi, Mongolian, Nepali, Norwegian, Norwegian Nynorsk, Occitan, Pashto, Persian, Polish, Portuguese, Punjabi, Romanian, Russian, Sanskrit, Serbian, Shona, Sindhi, Sinhala, Slovak, Slovenian, Somali, Spanish, Sundanese, Swahili, Swedish, Tagalog, Tajik, Tamil, Tatar, Telugu, Thai, Tibetan, Turkish, Turkmen, Ukrainian, Urdu, Uzbek, Vietnamese, Welsh, Yiddish, Yoruba, Yue Chinese AI features are available in: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai Why do I have to keep the app open while it is transcribing? The app has to be open during transcription as iOS limits apps from operating in the background for extended amounts of time. If you are unable to run the app at the moment, you can quit and reopen the app at any time. The interrupted recording will automatically start transcribing again. Terms of service: https://piquant-tile-b12.notion.site/Sono-Terms-of-Service-2dc141824eed803cae5ec5531f827eb2?source=copy_link Privacy policy: https://piquant-tile-b12.notion.site/Sono-Privacy-Policy-2dc141824eed80e3ba8bdecf4f55d04a?source=copy_link ACKNOWLEDGEMENTS: Sono uses the following third-party models: • Parakeet: "Parakeet TDT 0.6b v3" by NVIDIA, licensed under CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Converted to Core ML format by FluidInference. Source: https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3 • Whisper: OpenAI Whisper models (MIT License), run via WhisperKit by Argmax (MIT License) • Llama: Built with Llama. "Llama 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved." (https://www.llama.com/llama3_2/license/)