描述
VoiceToText is more than just a transcription app. It is a fully offline app that uses OpenAI Whisper, a state-of-the-art speech recognition model, to transcribe audio on your computer. This means you don’t need any internet connection or worry about your data being sent to any remote server. You can enjoy fast and secure transcription of your audio files, without compromising on quality or privacy.
Now with GPU Hardware Acceleration: Whisper UI takes a giant leap forward by integrating support for GPU hardware acceleration. Harness the power of your computer’s CPU, OpenCL, and NVIDIA CUDA (versions 12 and 11) to boost transcription performance significantly. This feature enables faster processing times and smoother operation, especially for lengthy or complex audio files.
Fully Offline Capabilities: Utilizing the advanced OpenAI Whisper speech recognition model, VoiceToText operates entirely offline. This ensures your transcriptions are processed on your device without requiring an internet connection, guaranteeing privacy and security.
New Feature: LLM-Powered Offline Subtitle Translation
VoiceToText now includes a groundbreaking feature that utilizes Large Language Models (LLM) to translate subtitles offline, leveraging the power of your computer. This new addition enhances the app’s capabilities, allowing you to:
With Whisper UI, you can:
- Transcribe audio from any format, including MP4, MOV, MKV, AVI, MJPEG, MPEG, F4V, FLV, M2T, M2TS, M2V, 3GP, 3G2, MP3, WAV, OGG, FLAC, M4A, M4V, AIFF
- Record and transcribe audio directly from your computer’s microphone or any audio input device
- Select the input audio language and output text language
- Translate audio from 57 different languages into English
- Specify source language of any of the 57 supported languages
- Generate subtitles in various formats, including .srt, .ass, .vtt, ssa. .lrc
- Download the generated text or subtitle file
- Edit or correct the transcription within the app
- Install as a background service for Scorpio Player to use live transcription and display subtitles using your own computer power
- Customize the app’s appearance with Mica, Mica Alt, Acrylic, or Dynamic Shader Animation backgrounds
- Translate subtitles offline: With the integration of LLM, you can now translate subtitles without an internet connection, ensuring your data remains private and secure.
- Utilize your computer’s power: The translation process is performed directly on your computer, using its processing capabilities to deliver quick and accurate results.
- Support for multiple languages: This feature supports translation between various languages, making it easier to work with international content.
VoiceToText is the ultimate app for anyone who works with audio content. It saves you time and effort by providing you with accurate and editable transcriptions in minutes. It also helps you communicate and collaborate with people from different languages and cultures by translating audio with a single tap.
Available models and languages
There are five model sizes, four with English-only versions, offering speed and accuracy tradeoffs. Below are the names of the available models and their approximate memory requirements and inference speed relative to the large model; actual speed may vary depending on many factors including the available hardware.
AI Subtitle Translator: Bridging Language Barriers with Precision
Our app proudly supports an extensive range of languages for translation, ensuring that your subtitles are accurately conveyed no matter the content. Here’s a detailed look at our supported languages:
- English (US): Experience translations with American idioms and cultural nuances.
- English (Great Britain): Enjoy the charm of British English with its unique spellings and expressions.
- Chinese Simplified: Navigate the modern simplicity of China’s most widely used writing system.
- Chinese Traditional: Retain the classic beauty of traditional Chinese characters in your subtitles.
- Arabic: Connect with the rich linguistic tapestry of the Arab world through precise subtitle translation.
- German: Immerse yourself in the linguistic depth of Germany with translations that capture its essence.
- French: Feel the romance of French cinema with subtitles that resonate with Francophone eloquence.
- Italian: Relish in the lyrical rhythm of Italian dialogue with subtitles that sing.
- Japanese: Dive into the intricate layers of Japanese storytelling with culturally aware translations.
- Korean: Engage with the vibrant energy of Korean media through accurate and timely translations.
- Portuguese: Embrace the diverse dialects of Portuguese-speaking countries with tailored subtitle translations.
- Russian: Explore the vastness of Russian literature and film with subtitles that do justice to its complexity.
- Spanish: Revel in the diversity of Spanish variants, from European to Latin American, all translated with care.
- Turkish: Immerse yourself in the storied tradition of Turkey with subtitles that capture the essence of its language and culture.
Memory usage
Model Disk Mem SHA
tiny 75 MB ~125 MB bd577a113a864445d4c299885e0cb97d4ba92b5f
base 142 MB ~210 MB 465707469ff3a37a2b9b8d8f89f2f99de7299dac
small 466 MB ~600 MB 55356645c2b361a969dfd0ef2c5a50d530afd8d5
medium 1.5 GB ~1.7 GB fd9727b6e1217c2f614f9b698455c4ffd82463b4
large 2.9 GB ~3.3 GB ad82bf6a9043ceed055076d0fd39f5f186ff8062
螢幕擷取畫面
新功能
- 版本: PC
- 發佈日期:
價錢
-
* 應用內購買 - 今天: $4.99
- 最小值: 免費
- 最大值: $4.99
追蹤票價
開發人員
- parmata
- 平台: Windows 應用程式 (21)
- 清單: 0 + 1
- 點數: 7 + 31 ¡
- 排名: 0
- 評測: 0
- 折扣: 11
- 影片: 0
- RSS: 訂閱
點數
-
- 66 Mirsao
排名
未找到 ☹️
清單
未找到 ☹️
評測
成為第一個評論 🌟
其他資訊
你可能還喜歡
-
- AI Text to Speech Studio - Voice Over and Cloning
- Windows 應用程式: 公用程式與工具 由: parmata
- $4.99
- 清單: 0 + 0 排名: 0 評測: 0
- 點數: 0 + 5 (2.0) 版本: PC AI Text to Speech Studio - Voice Over and Cloning Transform your text into lifelike speech with AI Text to Speech Studio, the ultimate voice-over and cloning app designed for seamless ... ⥯
-
- Text Comparator (Text Diff Tool)
- Windows 應用程式: 公用程式與工具 由: 25/8
- $12.99
- 清單: 0 + 1 排名: 0 評測: 0
- 點數: 2 + 0 版本: PC Text Comparator is a text diff tool that compares 2 texts from different sources and evaluates if they match or not each other. ⥯
- -33%
- AI Voice Maker
- Windows 應用程式: 公用程式與工具 由: SCORPIOX
- $3.34
$4.99-33% - 清單: 0 + 0 排名: 0 評測: 0
- 點數: 0 + 0 版本: PC AI Voice Maker: Unleash Creativity with Intuitive Text-to-Speech Transform your text into lifelike speech with AI Voice Maker, the cutting-edge app that brings your words to auditory ... ⥯
-
- AI Robat Assistant - Answer Your Questions
- Windows 應用程式: 公用程式與工具 由: White Moonlight
- * 免費
- 清單: 0 + 1 排名: 0 評測: 0
- 點數: 3 + 42 (4.0) 版本: PC AI Robot Assistant is an innovative app designed to provide intelligent assistance for answering a wide range of questions. Powered by advanced AI technology, this app is your go-to ... ⥯
-
- Text to Speech Voice Reader
- Windows 應用程式: 公用程式與工具 由: Some Media Apps
- * 免費
- 清單: 0 + 1 排名: 0 評測: 0
- 點數: 0 + 79 (4.5) 版本: PC Text to Speech Voice Reader read out loud text for you, whether the text is written by you, copy and pasted from a webpage, or imported from a document. In addition, it provides a ... ⥯
- -60%
- Text To Speech Universal
- Windows 應用程式: 公用程式與工具 由: Mr Line
- $19.99
$49.99-60% - 清單: 1 + 1 排名: 0 評測: 0
- 點數: 3 + 0 版本: PC Text To Speech Universal Just paste your text and hit the read button. Supports more than 50 languages Multiple male and female narrators ⥯
- -50%
- Voice To Text Converter Pro
- Windows 應用程式: 公用程式與工具 由: aria vision
- $2.49
$4.99-50% - 清單: 0 + 0 排名: 0 評測: 0
- 點數: 0 + 0 版本: PC Voice To Text Converter Pro supports all audio formats and languages worldwide, enabling seamless conversion of large files into accurate, editable text. Process lengthy recordings ... ⥯
-
- text to speech & mp3
- Windows 應用程式: 公用程式與工具 由: 韵华软件
- * 免費
- 清單: 1 + 0 排名: 0 評測: 0
- 點數: 0 + 9 (3.6) 版本: PC Text To Speech (TTS) Read aloud for any text (write your own or text file),and TXT,RTF , DOCX/DOC files. Listen to articles, or play-back your own texts. Select announcers. Change the ... ⥯
-
- Text to Speech Tool
- Windows 應用程式: 公用程式與工具 由: Applite
- 免費
- 清單: 0 + 1 排名: 0 評測: 0
- 點數: 1 + 4 (3.0) 版本: PC Text to Speech Tool is the a converter of plain text to Speech. Supports Male and Female voices. Word being spell will be highlighted. How To Guide: - Launch App - Type text in the ... ⥯
-
- AI Subtitle Creator PRO
- Windows 應用程式: 公用程式與工具 由: Art Group
- * 免費
- 清單: 0 + 1 排名: 0 評測: 0
- 點數: 0 + 0 版本: PC AI Subtitle Creator PRO is an innovative application designed for easy and efficient subtitle creation. The core function of the app is the automatic creation of subtitles based on ... ⥯
-
- VOICE CLOCK
- Windows 應用程式: 公用程式與工具 由: KAB Studio
- $0.99
- 清單: 0 + 0 排名: 0 評測: 0
- 點數: 1 + 2 (2.0) 版本: PC Voice Clock is an application that tells current time the way people do. This clock prints out time differently every minute. It s either 'Fifteen minutes past eight', or 'Forty-five ... ⥯
-
- Text to Speech Prime
- Windows 應用程式: 公用程式與工具 由: Indus Valley Apps
- $1.49
- 清單: 0 + 0 排名: 0 評測: 0
- 點數: 0 + 2 (2.5) 版本: PC Text to Speech Prime is easy to use and one click away the operation like play, pause, stop and manipulate the speech in offline without any privacy issues of the text. We can save ... ⥯
-
- AI Image Generator Plus
- Windows 應用程式: 公用程式與工具 由: Nova Laboratory
- $19.99
- 清單: 0 + 0 排名: 0 評測: 0
- 點數: 0 + 0 版本: PC AI Image Generator Plus is your passport to a realm of boundless creativity. With over 20 diverse models and styles, this app empowers artists, designers, and imaginative minds to ... ⥯
-
- Audio Pipes
- Windows 應用程式: 公用程式與工具 由: Racer159
- * 免費
- 清單: 0 + 0 排名: 0 評測: 0
- 點數: 0 + 3 (5.0) 版本: PC Audio Pipes allows you to route audio from any file or device to another file or device on your computer. This enables a wide variety of potential uses such as: - Connect a HAM radio ... ⥯