Simple Pricing - Superior Quality

Frequently Asked Questions

How can VocalStack's AI improve my transcription quality?

VocalStack uses large language models (LLMs) to get the best transcription quality possible, even in the most challenging audio environments. This includes Whisper, which serves as the core model for the VocalStack platform. The large Whisper model is a state-of-the-art AI model that has been trained on a vast amount of data to understand and transcribe speech accurately.

To better understand the impact of an AI model's size, let's use the different Whisper models to transcribe a fictitious excerpt:

Perfect Audio

97%

Model Size: Large-v3

DifferenceRaw Text

Difference

In a quaint little cafée near the Thames, Claire chuckled as Pierre ate eight eclairs all in one go. Anticipating gastroesophageal reflux, he said, "nNope, they're not worth it!". Later, they called a Lyft to drive them to the park, as Pierre thinks it's cheaper than Uber. As they walked under the glow of the noctilucent sky, they jumped when they'd seen a bear clothed only in his bare fur. Pierre cried out loud, "Mon Dieu!" They both leapt hastily into the river and swam for Chiswick Eyot. "Phew!"

Original Text

In a quaint little café near the Thames, Claire chuckled as Pierre ate eight eclairs all in one go. Anticipating gastroesophageal reflux, he said "nope, they're not worth it!" Later, they called a Lyft to drive them to the park, as Pierre thinks its cheaper than Uber. As they walked under the glow of the noctilucent sky, they jumped when they'd seen a bear clothed only in his bare fur. Pierre cried out loud, "Mon Dieu!" They both leapt hastily into the river and swam for Chiswick Eyot. Phew!

If my transcribed audio is less than an hour, will I be billed for the whole hour?

No, you will not be billed for the whole hour. Our billing costs are always calculated per second of transcribed audio regardless of whether the transcription is a prerecorded audio or live audio. This means you only get billed for what you need transcribed. The only exception is that the audio must be at least one minute long. Otherwise, you will be billed for the whole minute.

To simplify this further, here is what you will be billed in each plan for a prerecorded transcription (assuming you've used up all your free transcription hours for the month):

30 minutes

Hobby Plan Prerecorded Transcription Cost

$0.3500

Premium Plan Prerecorded Transcription Cost

$0.1750

Are there hidden costs? Do I have to pay for translations, summarizations, etc?

No, there are no hidden costs. You only pay for the transcription of your audio content. (In other words, only for the costs listed on the pricing table.) Other features such as automatic language detection, translations, summarizations, paragraph segmentation, keyword detection, and timestamps are included for free.

Importantly, the number of translations does not affect the transcription cost. For example, if you transcribe an audio file in English and then translate it into Spanish, French, and German, you will only be billed for the transcription of the English audio. This also applies to live transcriptions using Polyglot. You can perform an unlimited number of translations at any time without any additional charges.

What is the difference between live and prerecorded transcriptions?

Pre-recorded transcription refers to the process of transcribing audio that has been previously recorded. It can be uploaded as an audio file and transcribed at a later time, making it suitable for podcasts, interviews, videos, and other recorded content.

Live transcription refers to the process of transcribing audio in real time as it is being spoken. This is useful for live streams, podcasts, events, meetings, lectures, and other scenarios where immediate transcription (and possibly translation) is required

What languages does VocalStack support?

Support for over 57 languages, including different dialects and accents. Supported languages include: Afrikaans, Arabic, Armenian, Azerbaijani, Belarusian, Bosnian, Bulgarian, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, Galician, German, Greek, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Kannada, Kazakh, Korean, Latvian, Lithuanian, Macedonian, Malay, Marathi, Maori, Nepali, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Slovenian, Spanish, Swahili, Swedish, Tagalog, Tamil, Thai, Turkish, Ukrainian, Urdu, Vietnamese, and Welsh.