FANTASTIC
The savings in man-hours pays for my 5-codes. I'm super pleased and eager to see what else I can use this for.
Tried a few other solutions to create start and end timestamps for audio files. We take those timestamps and create audio read along PHP files for a client's online program.
We have struggled automating this task due to hallucinations, muddled output text, and the like. This process has been a burdensome, manual process. The output in our initial test on Salad went so smooth!
This project is now being escalated for completion.
Setting up the AWS S3 Bucket took me a minute to refresh my memory. Would be nice to submit files using other methods. Other than that--- Big thumbs up.
Affordable price for voice Whisper-based recognition services
I've been using Google Colab for Whisper for a long time, but it wasn't always comfortable and efficient. This service allows transcribing at a much lower cost compared to using the OpenAI API or Colab Pro and offers the added benefit of a distributed environment feature. I believe this service will be valuable for numerous cases. The team is very proactive and responsive.
Just today, they published an article on how to use the API in Zapier, which helped me implement Webhooks in Activepieces. This level of support and documentation is greatly appreciated.
The speed and accuracy of transcriptions have been impressive so far. The ability to integrate with various automation platforms (Activepieces, Make, n8n, etc) through well-described API and Webhooks adds significant flexibility to the service.
Overall, this service offers a compelling alternative to more expensive options in the market, especially for those needing reliable, cost-effective voice recognition capabilities.
A freaking nuclear reactor for adding transcription to your own services!
I use a LOT of transcription services. We are a research company and record and transcribe interviews in bulk. However, getting a service that not only provides API for high-quality transcription, but also speaker identification, and sentence breakdowns has proven tricky. And getting one as a LTD was basically an impossibility. Until Salad.
If you want to build powerful transcription workflows into your existing tech ecosystem, then Salad is the best I've found.
Also, note that the Salad transcription is returned as a JSON script, with a LOT (and I mean a LOT!) of information you do not get from 'out of the box' transcription services.
In short, Salad Transcription API is a backend service to power YOUR OWN solutions. It is a developer-oriented service. If you are not a code nerd or do not have access to a coder, then this product is probably not for you.
But if you have the need to transcribe-enable all your workflows... then I've not found a better value or higher quality product.
Summary:
If you are looking at transcription that can identify speakers and provide outputs in a programatic form, Salad is a must-have deal. I purchased tier 5, which is roughtly twice the amount of recording time we currently use. I want ht headroom as with this tool, I can do a whole lot more with transcription. In short, a must-buy for developer-minded folks.