Scrib
On-device voice transcription. Your audio never leaves your phone.
新版本 0.18
• Fixed switched-away models staying resident in memory
• Fixed streaming Zipformer exports detected as offline ones
• Fixed streaming Zipformer exports detected as offline ones
Scrib turns speech into text entirely on your device, using open Whisper speech models. Nothing is uploaded — the app only goes online to download a model you choose.
Two ways to use it
• Transcribe your own audio. Pick any audio file on your phone and get the text, right in the app, fully offline.
• A transcription engine for other apps. Scrib also runs in the background. Apps that support it — such as Forkgram — can turn a voice message into text through Scrib, on your device. In that app's settings, choose Scrib as the offline transcriber.
Models
Scrib transcribes with open Whisper speech models. Download one on the main screen, or pick your language and Scrib fetches a suitable one. Larger models are more accurate but slower and bigger to download; keep several and switch any time. You can also add any whisper.cpp-compatible model by direct link, or import a .bin from your device. Models are downloaded separately and are not bundled in the app.
Privacy
Transcription runs 100% on device. Your voice messages never leave your phone. The only network access is downloading a speech model you pick.
For developers
Any app can use Scrib as an offline transcriber through the open Open Transcribe contract (org.opentranscribe.api) — a small AIDL service, no SDK and no network. The contract is vendor-neutral, so apps aren't tied to Scrib: they can bind any compatible transcriber the user has installed.
Two ways to use it
• Transcribe your own audio. Pick any audio file on your phone and get the text, right in the app, fully offline.
• A transcription engine for other apps. Scrib also runs in the background. Apps that support it — such as Forkgram — can turn a voice message into text through Scrib, on your device. In that app's settings, choose Scrib as the offline transcriber.
Models
Scrib transcribes with open Whisper speech models. Download one on the main screen, or pick your language and Scrib fetches a suitable one. Larger models are more accurate but slower and bigger to download; keep several and switch any time. You can also add any whisper.cpp-compatible model by direct link, or import a .bin from your device. Models are downloaded separately and are not bundled in the app.
Privacy
Transcription runs 100% on device. Your voice messages never leave your phone. The only network access is downloading a speech model you pick.
For developers
Any app can use Scrib as an offline transcriber through the open Open Transcribe contract (org.opentranscribe.api) — a small AIDL service, no SDK and no network. The contract is vendor-neutral, so apps aren't tied to Scrib: they can bind any compatible transcriber the user has installed.
- 作者: 23rd
- 许可: GNU General Public License v3.0 or later
- 问题跟踪系统
- 源代码
- 构建元数据
- 可重复性状态
版本
尽管下面提供了 APK 安装包的下载选项，但你应该注意，以这种方式安装将不会收到更新通知，这是一种不太安全的下载方式。 我们建议你安装使用 F-Droid 客户端。
下载 F-Droid-
arm64-v8a该版本需要 Android 8.0 及以上版本。
此安装包由 F-Droid 构建并签名，且保证与此源代码 tarball 保持一致。
-
arm64-v8a该版本需要 Android 8.0 及以上版本。
此安装包由 F-Droid 构建并签名，且保证与此源代码 tarball 保持一致。
-
arm64-v8a该版本需要 Android 8.0 及以上版本。
此安装包由 F-Droid 构建并签名，且保证与此源代码 tarball 保持一致。
新版本 0.15
• Added bounding of Sherpa external-data scan
• Fixed Sherpa VAD slowing short-file transcription
• Fixed Sherpa VAD slowing short-file transcription
新版本 0.12
• Fixed misclassification of legacy streaming model types
• Added import support of Moonshine and Canary models
• Added Sherpa VAD processing of speech segments
• Added import support of Moonshine and Canary models
• Added Sherpa VAD processing of speech segments