
Texter: Audio & Video to Text
生產力
免費 · App內購買 · 專為 iPad 設計
Are you spending countless hours transcribing meetings, interviews or lectures
Texter is an AI transcription app that turns audio, images and video into editable text with a single tap. From meeting minutes and interview notes to subtitles and SRT files, you can handle your entire workflow in one place.
Key new features
・Silence cut
Automatically detects and removes silent sections in audio and video. Perfect for meetings and lectures with long pauses. Choose from three presets Low, Standard and High and preview the result in real time.
・Synced subtitles on video import
Generate subtitles with timestamps when you import a video. Subtitles stay in sync as you play, which makes reviewing and editing much easier for lectures, interviews and recorded meetings.
・Sentence based view and editing
Display your transcript as a list of sentences. Jump to the exact playback position for each sentence with one tap, so you can quickly find, fix and share just the parts you need, even in long multi speaker recordings.
・Improved high accuracy speech recognition
Latest speech recognition technology, including on device models on supported devices, gives you fast and readable transcripts. Clean subtitles make editing, summarizing and searching much smoother.
Why people choose Texter
・Highly accurate transcription with the latest AI and on device technology
・Extract audio from video, auto create subtitles and edit by sentence with time jump
・Summarize and translate transcripts to turn them into clean meeting minutes
・Real time translation using DeepL and Google, both online and offline
・Turn images, photos, PDFs and screenshots into text with multi page PDF support
・Real time transcription that can also support people with hearing difficulties
Use cases
・Meetings
Import recordings, review subtitles and the sentence list, then share only the important parts.
・Interviews and journalism
Split by speaker, edit by sentence and dramatically cut down editing time.
・Classes and lectures
Pull out key points from lecture videos and make searchable, summarized notes.
・Creators
Convert video to text, edit subtitles and export clips for social media, all in one app.
・Export
Export transcripts as PDF or SRT subtitle files and use them directly in documents or video editing.
Texter Premium
・Remove limits on real time transcription and image text recognition
・Increase maximum length for imported audio
・Remove ads for a smoother experience
Notes
・Some advanced features work even better on newer iOS devices and OS versions.
・Transcription and subtitle accuracy depends on recording quality, such as noise level and clarity of speech. You can always edit the text later.
We will keep improving Texter based on your feedback. Please give it a try.
Terms of Use
https://sites.google.com/view/texter-voice-to-text/terms-of-service
Personal Information Protection Policy
https://sites.google.com/view/texter-voice-to-text/privacy-policy#h.p_xa805c26EeZ5
評分與評論
此 App 尚未收到足夠的評分或評論,無法顯示概覽。
What's New
Whisper Speaker Diarization
Now you can identify different speakers in your transcriptions using Whisper's speaker recognition feature. Perfect for meetings, interviews, and multi-person conversations.
• Automatically detect and label different speakers
• Works with Whisper transcription engine
• Clear visual separation between speakers
Other Improvements
• Enhanced app stability and performance
• Improved transcription accuracy
If you enjoy Texter, please consider leaving us a review!
開發者Yuichi Matsuoka指出App的隱私權實務可能包含下方描述的資料處理。如需更多資訊,請參閱 開發者的隱私權政策 。
用於追蹤你的資料
以下資料可能會用於追蹤你在其他公司的 App 和網站的活動:
- 使用資料
不會與你連結的資料
開發者可能會收集以下資料,但不會連結你的個人身份:
- 用户內容
- 識別碼
- 使用資料
- 診斷
輔助使用
開發者尚未表示此 App 支援的輔助使用功能。 進一步瞭解
資訊
- 供應商
- Yuichi Matsuoka
- 大小
- 197.1 MB
- 類別
- 生產力
- 相容性
須使用 iOS 16.0 或以上版本。
- iPhone
須使用 iOS 16.0 或以上版本。 - iPad
須使用 iPadOS 16.0 或以上版本。 - Mac
須使用 macOS 13.0 或以上版本及配備 Apple M1 或以上版本晶片的 Mac。 - Apple Vision
須使用 visionOS 1.0 或以上版本。 - Apple Watch
須使用 watchOS 6.0 或以上版本。
- 語言
日文和其他3種
- 日文、簡體中文、英文、西班牙文
- 年齡分級
4+
- 4+
- 包含
廣告
用户產生內容
- App內購買
是
- Premium 6months USD 24.99
- Real Time Cloud Translation+ USD 7.99
- +Import Audio(AWS Transcribe) USD 11.99
- Real-time high performance+5hr USD 11.99
- Long-time audio recognition. USD 55.99
- Long-time audio recognition. USD 27.99
- Unlimited Image Recognition. USD 9.99
- Premium 1year USD 53.99
- Unlimited Image Recognition USD 4.49
- 版權
- © Yuichi Matsuoka