This is an automatic transcription service using the latest available AI models. It provides a summarization of the text, in addition to the full transcript which includes capitalization and punctuation.
It typically takes 10 minutes to transcribe 30 minutes of audio/video. We will not finalize your payment until the transcript has been completed and emailed successfully.
Below is a recording of one of our Huntsville AI meetups, followed by the first few paragraphs of the automatically generated transcription. You can find more videos of our meetups along with transcripts provided by this service at https://hsv.ai/videos/
You can see like the previous sessions we've done this year going back to 2018, but it does get a little sparse the further back you go. When we first started, I think we met like five times the first year and then eventually we got into a rhythm.
So what we're talking about tonight is something called Faster Whisper. If you don't know, we actually have a transcription service. And of course, if you are on here and watching this live, if you do drop an auth token, it will let you transcribe stuff for free.
So how about it?
If I start to lose too much money that way, I will change the auth token.
So I also follow my own advice and there is a quota on that budget.
Huntsville AI Transcribe is a service offered by Huntsville AI, a community-driven organization dedicated to advancing artificial intelligence in the Huntsville, Alabama area. Our transcription service is part of our broader mission to make AI technologies accessible and beneficial to everyone. At Huntsville AI, we strive to build and support the local AI community through collaboration, education, and practical application. Our goal is to foster a network of individuals and organizations who work together to enhance AI knowledge and implementation, ultimately improving our quality of life. To get involved in our community, Subscribe to our bi-weekly mailing list.
The transcription service is built around the Whisper model from OpenAI. For each file transcribed, we create an instance of this model inside of a container which is disposed of after the transcript is completed and emailed. We do not keep copies of either the file to be transcribed or the final transcript. We do not use or sell your email or other data other than to create the requested transcript.
It is a bit slower because we're not using a GPU or special hardware, but it also makes it cheaper. Another benefit is that we do not have to worry about anyone outside of the transcription service having access to your files or transcripts.
If you need a similar transcription service created specifically to suit your needs, or if you have constraints around where your data can be stored - we can help.
Contact Us with your specific needs and we will reach out.
We use Google Analytics to help us determine how the service is being used and if we have problems with the workflow. There are cookies baked and consumed as part of this process.