FAQ speech to text

Speech to Text FAQ

We focus on building speech to text engines in different languages with the highest accuracy rate possible. Our service is cloud-based and we’ve developed an API to make sure you can integrate it in your existing software. To make sure you get a clear overview of our services, we’ve set up an FAQ page.

However, we strongly believe in customized service, so please don’t hesitate to contact us for specific questions about our service or roadmap.

What programming skills are needed to connect to your service?

Our service is exposed through an HTTP API, experience with developing against such an API is advised. But we help you to get started with a few implementation examples on our website.

Is the service completely cloud-based, does it work on-premise as well?

The service is 100% cloud-based, it runs on Azure actually. We do not offer an on-premise variant at this moment.

What security measures are taken, do you use encryption?

All connections from the Internet to the platform are secured with TLS, this means that nobody can eavesdrop on your data while in transit. Within the platform, we make use of disk encryption.

Do you store any data we send to your service?

We store your data while we are processing it after we are finished we remove everything again.

Can I process both real-time and in batch? If so, is there a difference in connecting to your service?

We do support batch processing and real-time. There will be a difference in connecting to the service, but we promise we will not make it too hard for you.

How much can we process at the same time, how long before we get results?

All files are uploaded to our cloud platform and processed sequentially, there are no limitations on the number of files we can process for you (although you can hit a quota). Response time will vary based on the length of your audio file, chosen language and queue length but averages to one minute of processing per 5 minutes of audio.

What type of files do you support?

At this moment we support WAV, MP3, AVI, MP4, OGG and much more. For a detailed list see our documentation.

What kind of languages will you develop in the near future?

We determine our roadmap based on our client’s requests. Please contact us to discuss the current roadmap and to see what possibilities we can offer you.

Contact us @ info@zoommedia.ai

Share this post