Transcripto
The cheapest way to transcribe speech to text
Second episode of "Making a Product: Transcripto" is out! In this one, Leo will show he designed a logo for Transcripto - by being lazy and leveraging the power of Artificial Intelligence. Not sure we will design next logos like this, but it was a fun experiment! :-) https://youtu.be/H9MXayQ3wP0
One of the secrets goals behind Transcripto was to launch a YouTube show about how we built it. From the day one we've recorded everything we do with the plan to make this videos. In February, "Making a Product: Transcripto" is ready for showtime, with the first two episodes already published on mkdev channel: https://youtu.be/jPM40mfDi_4
After another few weeks of polishing, killing bugs, improving the infrastructure and testing-testing-testing, we are ready to release Transcripto to public! We've prepared texts for all platforms like IndieHackers and ProductHunt and started posting it, like this post and timeline here :-)
In 1 month we built complete MVP, with all the features we planned, complete design, solid infrastructure on top of AWS, all automated and what not. From there just final touches are left and we are ready to release Transcripto to public!
My wife kept testing the application, uploading 60-90 minutes interviews in German language and using the result for her thesis.
Having the backbone of the app ready, @3LiON and I talked and decided, that everyone should have access to simple, cheap, reliable speech to text solution. You upload your file, pay per minute of transcribed audio and get the text back, that's it. So we rolled up our sleeves and got to work 👨💻🧑💻
My wife is finishing her thesis at the moment. 👩🏻🎓 As part of this thesis she needed to conduct around a dozen hour-long interviews, then transcribe them to text and do some analysis of it (all in German language).
She was telling me how huge the task of transcribing audio to text will be and how she will need hours and hours of extremely unrewarding work to do it. 🙇🏻♀️
Being a developer and a cloud infrastructure engineer myself, I helped her out and built an app. In this app, she could upload her audio files and get an accurate transcription back. All she had to do was to go through each transcription once, correcting few mistakes done by the machine. It saved her lots of time and, as you might know, happy wife - happy life. 🌞
Comment