Every day we offer FREE licensed software you’d have to buy otherwise.
Speech to Text Converter 5.2 was available as a giveaway on September 7, 2024!
Speech to Text Converter is an automatic speech conversion software to convert voice into text, supporting more than 50 languages. This audio to text utility can save you hours transcribing interviews, meetings, podcasts or any long audio files.
In addition to audio files (MP3, M4A, FLAC, WAV, OGG), this application also supports video files such as MP4, WEBM, MKV, AVI, MPEG, MOV, WMV, FLV, TS. It will automatically extract speech from any video file and convert to text. You can record your own voice using your microphone or load any audio file in order to convert to text. High quality audio improves results but you can also use narrow-band models for low-quality files.
If you have recorded some important lectures or speeches and want to convert them into text (transcription), you can either go the manual route of listening to the speech and typing the text or you can make use of the recent developments in the artificial intelligence (AI).
System Requirements:
Windows 7/ 8/ 8.1/ 10/ 11
Publisher:
VovsoftHomepage:
https://vovsoft.com/software/speech-to-text-converter/File Size:
97.9 MB
Licence details:
Lifetime with no free updates
Price:
$19.00
GIVEAWAY download basket
Comments on Speech to Text Converter 5.2
Please add a comment explaining the reason behind your vote.
iPhone app giveaways »
Android app giveaways »
Thank you for the offer. I'm excited to try it!
Save | Cancel
Does it support hebrew ?
Save | Cancel
Thank you for the giveaway.
When I click on the "Continuous Dictation" tab, it gives me this error popup:
No recognizer is installed.
OLE error 80045077, ClasslD:
{47206204-5ECA-11D2-960F-00C04F8EE628)
How can I fix this?
Save | Cancel
the system requirements on page https://vovsoft.com/software/speech-to-text-converter/ specifically state "(32-bit and 64-bit)" versions of windows but the portable build has a 64bit LGPLv3 licensed FFMPEG.EXE that cannot possibly execute under 32bit windows 7 to 10. The supplied Setup.exe has exactly the same problem a 64bit FFMPEG.EXE I presume that is used to convert varied input file formats to one standardised format for processing. Either way unless you replace that 64bit executable with a 32bit build of similar generation the program will not work as described under 32bit editions of windows, it will crash on importing sound files or just fail to import them if the error is trapped in the software. Note the software requires signing up to external platforms to use their speech to text engines and AI engines not many options exist without the use of external platforms Vosk and which requires .NET 4.8 to run and Microsofts Speech platform and it defaulted to dumping recorded wav files on my DESKTOP! Can't they use the %TEMP% variable and drop a subfolder in there Desktop is not a dumping ground for temporary recording files!
Save | Cancel
TK, no way to stop it dumping recordings to desktop Settings button does not provide a Setting for that just reveals login credentials for 3rd party AI and cloud services, don't expect it to be able to pick out a single voice in a crowd or just a small group of people speaking over each other... you need two ears and a decent auditory processing center for that and AI is not there yet.
Save | Cancel
I am sad, because there is Gujarati, Esperanto, Breton, but no Hungarian...
Save | Cancel
Mykee,
Bad luck, mate
Save | Cancel
Looks promising, supports offline and online models.including OpenAI Whisper.
Does it output time stamps? That's not mentioned anywhere, so I am guessing not. That would be an important feature to have for me. Outputting in SRT file format would be useful also.
Whisper model seems supoorted only as paid option. Use of downloaded Whisper model would also be great.
Save | Cancel
Alok, you mention SRT format for subtitles. Vovsoft has a free app for this, Speech to Subtitle Converter (both installer & portable) which converts voice audio in a variety of video formats to standard subtitle formats SRT & VTT. Haven't tried it yet, but it sounds very interesting. Also, to Mykee's point, Vovsoft's Speech to Subtitle Converter says it also supports Hungarian. [Homepage for Speech to Text Converter does say it supports Hungarian, tho...]
Here's the URL for Speech to Subtitle Converter: https://vovsoft.com/software/speech-to-subtitle-converter/
Save | Cancel
Alok, You say you want SRT output? Check out another Vovsoft's app which is freeware: Speech to Subtitle Converter
https://vovsoft.com/software/speech-to-subtitle-converter/
It outputs in SRT & VTT formats.
Save | Cancel
Nollo and Hubba.
Thanks. That looks useful.
I could not find about which model is used from Relplicate. So have no idea of how much charge a given audio would end up having on Replicate. Nevertheless, looks good and useful. I'll try to use. Thanks again.
Save | Cancel
It's a front-end for a range of free and chargeable speech recognition services, which is almost certainly the best way to do this. Also means it will improve over time as the services improve.
Save | Cancel