Speech to Text Converter Version History
Speech to Text Converter Changelog for the latest releases:This page contains the complete changelog of Speech to Text Converter, detailing what has changed in each version. Speech to Text Converter 5.4 December 13, 2024 (PST) - Hidden “Settings” ToolBar button when not needed
Speech to Text Converter 5.3 September 24, 2024 (PST) - Supported loading audio files using command line parameters
- The application remembers last used engine and language
- “Show in Explorer” opens “models” directory for non-existent model files in “Add language for Vosk” window
- Improved language list of Vosk
Speech to Text Converter 5.2 June 28, 2024 (PST) - Added “Add” button for Vosk
Speech to Text Converter 5.1 June 10, 2024 (PST) - Embedded offline French language model for Vosk, in addition to English
- Supported multiple language models for Vosk
- Renamed Vosk “model” directory to “models”
- Fixed encoding problem for Vosk
Speech to Text Converter 5.0 June 1, 2024 (PST) - Supported Vosk (offline speech to text engine)
- Improved UI
Speech to Text Converter 4.4 May 24, 2024 (PST) - Supported M4A audio files
Speech to Text Converter 4.3 February 16, 2024 (PST) - Added “Auto Detect” into Deepgram
- Improved timeout for Deepgram
Speech to Text Converter 4.2 October 18, 2023 (PST) - Fixed mutex bug in installer
- Improved UI
Speech to Text Converter 4.1 October 4, 2023 (PST) - Implemented OpenAI file size confirmation
- Increased OpenAI response timeout
- Fixed OpenAI bug
- Fixed drag and drop bug
Speech to Text Converter 4.0 September 5, 2023 (PST) - Supported OpenAI Whisper API
- Supported Deepgram API
- Improved UI
Speech to Text Converter 3.1 April 25, 2023 (PST)
Speech to Text Converter 3.0 March 7, 2023 (PST) - Supported Microsoft Azure Cognitive Services API
Speech to Text Converter 2.3 January 22, 2023 (PST) - Supported Swedish
- Default language model is now en-US_Multimedia
Speech to Text Converter 2.2 December 17, 2022 (PST) - Added “Convert Video to Audio Before Uploading” option
- Included FFmpeg
Speech to Text Converter 2.1 September 19, 2022 (PST) - Added hint image to “Continuous Dictation”
- Improved error messages
- Improved UI
Speech to Text Converter 2.0 September 16, 2022 (PST) - Added “Continuous Dictation” tab
- Implemented “No speech detected” dialog
- Improved UI
Speech to Text Converter 1.5 July 25, 2022 (PST) - Supported next-generation language models
- Fixed “file in use” problem
- Implemented gradient toolbar
Speech to Text Converter 1.4 October 31, 2021 (PST)
Speech to Text Converter 1.3 September 30, 2021 (PST) - Fixed error handling bug
- Improved UI
Speech to Text Converter 1.2 March 25, 2021 (PST) - Improved recording with microphone
Speech to Text Converter 1.1 December 27, 2020 (PST) - Fixed “Error sending data (12175)“ problem occurring in Windows 7
Speech to Text Converter 1.0 December 7, 2020 (PST) |
We are always working to improve our software for a better user experience!
Please make sure you are up to date to avoid any known issues and to get the best of what the software has to offer!
Got an idea for future releases?
Feature Requests