Tech blog
-
2026.04.24"Speech segment ratio" as seen in operational data
"How much does speech recognition actually cost?" -- To accurately understand the cost of the AmiVoice API, which charges only for the spoken portion, it's crucial to know the actual "speech segment ratio." This article analyzes the distribution of "speech segment ratios" based on real-world operational data. We'll provide concrete figures to give you an idea of the costs for each usage scenario, such as call centers, smartphone apps, and conference recordings. Please use this information to help you estimate costs before implementation.
-
2025.07.29[We Tested It!] How does speech recognition accuracy change with sampling rate and compression rate?
Have you ever wondered things like, "Won't the accuracy of speech recognition decrease unless the data is of high quality?" or "I want to reduce the file size, but how much compression is safe?" when using a speech recognition service? This time, we actually tested the effects of sampling rate and compression rate on speech recognition accuracy.
-
2023.06.26Comparing the speech recognition rates of OpenAI's Whisper and AmiVoice for "conference" audio
We compared the speech recognition accuracy of OpenAI's Whisper and AmiVoice for meeting audio. The results showed that AmiVoice had significantly fewer misrecognitions and was more accurate. We will explain the factors behind this difference, including examples of Whisper's misrecognitions.
-
2023.03.13Measuring the speech recognition rate of OpenAI's Whisper (AmiVoice VS Whisper)
In September 2022, OpenAI released a speech recognition engine called Whisper. We compared the speech recognition accuracy of Whisper and AmiVoice.
-
2021.10.25We thoroughly compared the voice recognition rates of AmiVoice and Google using electronic medical record input voice!
In a previous article, we compared the speech recognition accuracy (speech recognition rate) of AmiVoice's general-purpose engine and domain-specific engine, and received many comments from people who were curious about AmiVoice vs. Google. So, this time we compared the speech recognition rates of AmiVoice Cloud Platform and Google Speech to Text.
-
2021.06.28Comparing the appearance of "Recognition accuracy (recognition rate) XX%"
Even if you see a number like "The speech recognition accuracy (recognition rate) is XX%," it's hard to tell just by looking at it how accurately it's recognized. In this article, we'll compare sentences with recognition accuracy rates of 50%, 80%, 90%, etc. with the correct answer and explain the visual differences!
Most viewed articles
-
A quick explanation of how speech recognition works!
-
Comparing the speech recognition rates of OpenAI's Whisper and AmiVoice for "conference" audio
-
How to use the AmiVoice API free coupon
New articles
-
How to use coupons for Zenn Spring 2026
-
"Speech segment ratio" as seen in operational data
-
AmiVoice API Update Explanation: New Parameters for Voicebots Reduce Response Wait Times
Category list
- Introduction to Speech Recognition (15)
- How to improve voice recognition accuracy (12)
- I tried developing it (27)
- How to use AmiVoiceAPI(27)
- Comparison and Verification (6)
- Others(10)
Archive
