Introducing Powerful AI-based Transcription
Transcriber uses industry-standard AI models to automatically transcribe and create subtitles in sync with your video. It’s as simple as dropping a video file, selecting a language and pressing the transcribe button. Export the transcription as plain text, subtitles in SRT format, RTF with timecode reference, or send it to Final Cut Pro to create a timeline with the imported subtitles using the specified font and style.
- Batch Transcription: Transcriber now supports batch transcription, allowing users to transcribe multiple files or entire folders at once. Users can select the language and format, specify where the files should be saved, and customize file names. Transcription occurs in the background, making it convenient for processing large numbers of files.
- Timecode Retention: The new version retains the timecode of the source movie, aiding in better synchronization of subtitles and RTF files generated.
- New RTF Controls: Enhanced preferences for exporting files in RTF format have been added. Users can choose whether to include timecode and group texts into longer blocks based on word count or duration.
- Artificial Intelligence Improvements: Users can now control the minimum length of a sentence to filter out potential errors from the artificial intelligence. Additionally, Transcriber supports multiple models (Large, Medium, and Small) from OpenAI's Whisper, significantly increasing transcription speed.
- Language Fidelity: A new control allows certain languages such as Greek, Chinese, and Korean to be transcribed with higher accuracy.
- FPS and Frame Size Control: Advanced settings for exporting to Final Cut Pro now include options to specify the resolution and frames per second of the timeline. These settings are also available in the batch export window and for individual files.
- Recent Files: The onboarding screen features a new section displaying recent files, enabling users to open them quickly for editing.
New in Transcriber 1.2: AI Metadata
Create titles, keywords, summaries, and even images with the power of AI in just a few clicks.
Generate essential content such as titles, keywords, and summaries directly from their transcriptions. Simply navigate to the new “AI Metadata” tab, select your desired prompts, and watch as AI produces tailored responses. From YouTube optimization to social media readiness, this feature streamlines your workflow and enhances visibility. Furthermore, users can create images using OpenAI's Dall-E models, providing a comprehensive toolset for any content creator.
New in Transcriber 1.2: AI Punctuation
Use artificial intelligence to improve subtitle punctuation.
It can sometimes happen that the Whisper model cannot identify any punctuation for a certain portion of transcribed audio, so very long subtitles can be generated that would result in difficult readability. The new version of Transcriber can use ChatGPT (by supplying an API key) to improve punctuation. Subtitles are parsed and necessary punctuation added. Sentences are automatically split to be shorter and more readable.
How do I install Transcriber?
Transcriber for Apple and Intel processors is available via FxFactory, our app store for visual effects, audio plugins and apps:
If FxFactory is already on your system, or once you have completed the installation, click the button below to download and install Transcriber:
Version History
Transcriber 1.22.2
Transcriber 1.22.0
Transcriber 1.20.1
Transcriber 1.19.0
Allows play back at 1.5 or 2X the normal rate to speed up review.
Transcriber 1.18.6
Transcriber 1.17.0
Transcriber 1.16.4
Transcriber 1.15.3
Transcriber 1.15.0
Transcriber 1.14.0
Transcriber 1.13.4
Requires macOS 12.6 or later
Please note that this product will not work unless FxFactory is installed on the system.