Here are the features requested by users.
π We will try to implement the features with the most votes first.
π A valid license key must be entered for voting!
π Each license key can be used for a maximum of 1 vote per feature!
π A universal license key can be used to vote for all programs, even the freeware tools!
| Ability to download and install Vosk language packs automatically |
| Make it multilingual |
| Ability send the recognized text to clipboard automatically |
| Ability send the recognized text to file automatically |
| Ability to change font settings |
| Ability to change timeout value |
| Ability to convert multiple files at once |
| Ability to convert very large files |
| Ability to work like a barcode scanner (the user presses a button to βStart Listeningβ, and whatever they say gets converted to text and placed wherever their cursor is) |
| Add support for "Google Speech to Text" (60 minutes per month free) https://cloud.google.com/free |
| Fix freeze problem during uploading and waiting for server response |
| Fix long "microphone recording" bug. A 192 kbps 12-minute footage has already caught on and keeps stopping with an error. |
| Replace language codes with actual language names |
| Support more engines: - Windows local speech input (Windows-key plus "h" for human (voice) input.) - Web speech API - Speechmatics - Vocapia - Apptek - Phillips SpeechLive |
| Done π | Ability to convert video files such as MP4 |
| Done π | Ability to export the transcribed text as SRT or VTT to use in subtitling Developer Note: Published as new software: Speech to Subtitle Converter |
| Done π | Add Russian language |
| Done π | Auto-detect language |
| Done π | Support more engines: - Open AI Whisper (can be installed locally for on-prem use) - Deepgram (very fast and low cost), great for live audio |