One topic, one workspace
Keep several sources together. Originals, edited text and audio stay separate. Rename, export or remove them when you want.
DocsToSpeech · Listen to your own documents
Your documents.
Ready to listen.
Import a PDF, EPUB, note, Markdown file, photo or scan. Check the text, preview a bundled Chinese or English voice, or save the audio. Saved files stay in the audio library for resume, speed and repeat. Playback does not synthesize again.
View on the App Store iOS 17+ · Documents stay on this device
PDF · EPUB · Notes · Scans
On-device text recognition
Chinese and English voices
Listen · Create and save
Audio library
Shortcuts
简体中文
把自己的资料，变成随时能听的音频。
导入自己的 PDF、EPUB、笔记和扫描页。校对文字后，用内置中英文男声或女声试听，或生成并保存。资料留在本机。
Contact
Listen before you save
Text to audio has Listen and Create and save. Listen only plays. A saved file stays on the device and still plays after a restart.
Text from a page or a screenshot
Recognition runs on the device. After a screenshot, photo, capture or scan, compare the text with the original before you add it to a workspace.
Shortcuts
Tools includes an offline guide. The Shortcuts app can run Recognize text offline and Create offline audio.
What this version does
- Import your own PDFs, EPUBs, text, Markdown, photos and scans
- Bundled CosyVoice Chinese and English male and female voices; no separate voice pack
- Or choose a system voice already installed on the device
- The audio library plays saved local files that passed their checks
- Sign in with Apple is optional local identity and does not create a cloud account
- No ads and no analytics SDK. Materials are not uploaded automatically
Not in this version
Cloud AI explanations, business accounts, credit billing, document sync and audio or video transcription are not enabled. This version organizes, recognizes, speaks and replays material on the device. Finishing playback does not prove that the material is mastered. Models are bundled, so the download is large.
Questions
How do I listen to my own PDF on iPhone?
Create a workspace and import the PDF. Check the extracted text. Scanned pages use on-device recognition, and you can correct them. Then listen, or create and save, and play the file from the audio library. Steps are on the support page.
Do I install a voice pack separately?
No. Chinese and English male and female voices are already in the app. You can also use a system voice that is installed on the device.
Does replay need a network or another synthesis?
Saved audio plays from the device. It is not synthesized again. Export a copy yourself when you want one outside the app.
Are documents uploaded?
They are not uploaded automatically. Documents, recognition results and audio stay on this device. See the privacy policy.