Accurate audio transcription with speaker identification, powered entirely by on-device AI. Your audio never leaves your iPhone.
No servers, no uploads, no accounts. Stenio processes audio using on-device machine learning, so your conversations stay yours.
Audio never leaves your device. No cloud uploads, no analytics, no tracking. Your transcriptions are stored locally and are fully under your control.
Automatically identifies who said what with color-coded labels. Rename speakers to keep your transcripts clear.
Record directly in-app with real-time waveform visualization and live transcription preview.
Powered by WhisperKit, delivering accurate speech-to-text with timestamped, segmented output you can edit.
Supports MP3, M4A, WAV, AIFF, AAC, CAF, and MP4. Import from Files, or share directly from any app.
Queue multiple audio files and let Stenio transcribe them sequentially. Perfect for processing a backlog of recordings.
Generate bullet-point summaries of key topics, decisions, and action items — all processed on-device using Apple Intelligence.
Instantly search across all your transcripts by file name, speaker name, or content. Your entire history, always at hand.
Get accurate transcripts in minutes without sending a single byte to the cloud.
Record audio directly in Stenio, or import files from your device. Share from any app using the iOS Share Extension.
WhisperKit processes your audio entirely on your iPhone's Neural Engine. Choose from three model sizes to balance speed and accuracy.
Browse timestamped, speaker-labeled transcripts. Edit text, rename speakers, and generate summaries — all offline.
Three sizes to match your needs. Downloaded once, runs forever — no internet required after setup.
Last updated: March 28, 2026
Stenio is designed with a simple privacy principle: your data stays on your device. We do not collect, transmit, or store any personal information whatsoever.
Stenio does not collect any data. There are no analytics, no tracking pixels, no crash reporting services, and no telemetry of any kind. We have no servers that receive data from the app.
All audio transcription and speaker identification is performed entirely on your device using on-device machine learning models. Your audio files and recordings are never transmitted to any external server or third-party service. Audio data remains in the app's local storage on your iPhone.
Stenio requests microphone access solely for the purpose of recording audio within the app. Microphone data is used only for local recording and on-device transcription. No audio captured by the microphone is ever transmitted off your device.
Stenio does not require or offer user accounts. There is no sign-up, no login, and no authentication. You can use the app immediately after downloading it.
Stenio does not integrate with any third-party services that collect user data. The app uses WhisperKit for on-device speech recognition and SpeakerKit for on-device speaker identification — both run entirely locally on your device.
On iOS 26 and later, Stenio can generate on-device summaries using Apple's Foundation Models framework. This processing also occurs entirely on your device.
All transcripts, audio files, and settings are stored locally on your device in the app's sandboxed storage. This data is protected by iOS security features including device encryption. You can delete any or all of your data at any time from within the app.
Because Stenio does not collect any data from any user, it does not knowingly collect data from children under 13.
If we update this privacy policy, we will post the new version on this page and update the "Last updated" date above.
If you have questions about this privacy policy, please contact us at peters.thomas.a@gmail.com.
Last updated: March 28, 2026
By downloading or using Stenio ("the App"), you agree to the following terms. If you do not agree, please do not use the App.
Stenio grants you a limited, non-exclusive, non-transferable, revocable license to use the App on any Apple device that you own or control, subject to the Apple Media Services Terms and Conditions.
Stenio is an audio transcription application that uses on-device machine learning to convert speech to text and identify speakers. All processing occurs locally on your device. The App does not require an internet connection after the initial AI model download.
You agree to use Stenio in compliance with all applicable laws. You are solely responsible for the content you record and transcribe. You must ensure you have proper consent from all parties before recording conversations, in accordance with applicable local, state, and federal laws.
Stenio uses machine learning models to generate transcriptions. While we strive for accuracy, transcriptions may contain errors. You should not rely on Stenio transcriptions as a sole authoritative record without review. The App is not intended for use in medical, legal, or other contexts where transcription errors could cause harm.
The App and its original content, features, and functionality are owned by Stenio and are protected by copyright, trademark, and other intellectual property laws. The App uses open-source components, including WhisperKit, which are licensed under the MIT License. Acknowledgments are available within the App.
The App is provided "as is" and "as available" without warranties of any kind, either express or implied, including but not limited to implied warranties of merchantability, fitness for a particular purpose, and non-infringement.
To the maximum extent permitted by law, Stenio shall not be liable for any indirect, incidental, special, consequential, or punitive damages, or any loss of profits or revenues, whether incurred directly or indirectly, or any loss of data, use, goodwill, or other intangible losses.
We reserve the right to modify these terms at any time. Updated terms will be posted on this page with a revised date. Continued use of the App after changes constitutes acceptance of the new terms.
These terms shall be governed by and construed in accordance with the laws of the jurisdiction in which the developer resides, without regard to its conflict of law provisions.
For questions about these terms, contact us at peters.thomas.a@gmail.com.
We're here to help
Have a question, found a bug, or want to share feedback? Reach out and we'll get back to you.
Only for the initial one-time download of the AI model (150–626 MB depending on which size you choose). After that, Stenio works completely offline — no internet required.
No. All transcription and speaker identification happens entirely on your iPhone. Your audio files never leave your device. There are no servers, no cloud processing, and no data collection of any kind.
Stenio supports MP3, M4A, WAV, AIFF, AAC, CAF, and MP4 files. You can import files from the Files app or share them directly from other apps using the iOS Share Extension.
We recommend the Large model for the best accuracy. The Small model is faster but less accurate, while the Medium model offers a balance between speed and quality. You can change your model at any time in Settings.
Stenio uses on-device speaker diarization to automatically detect different speakers in your audio. Each speaker is assigned a unique color-coded label. You can rename speakers to real names, and those names can be saved globally for future transcripts.
Yes. You can edit the text of any individual segment in a transcript, rename speakers, rename the transcript file, and delete segments or entire transcripts as needed.
On devices running iOS 26 or later, Stenio can generate bullet-point summaries of your transcripts using Apple's on-device Foundation Models. Summaries highlight key topics, decisions, and action items — all processed locally on your device.
You can delete individual transcripts or clear your entire history from within the app. You can also remove stored audio files while keeping the transcript text. Deleting the app removes all data since everything is stored locally on your device.