π£
Engaging Students with VideoStew: Real-Life Examples and Practical Guide
Digital Transformation of Education Using AIIn today's educational landscape, digital transformation is no longer optional but a necessity.Especially with the i...
Junwoo
2024-09-04
π
Short-Form Content Strategy for Media Companies: 3 Key Tips for Running a Successful YouTube Channel
Recently, traditional newspapers and online news outlets have been paying attention to short-form content. This is a strategic move to adapt to the changing tre...
Junwoo
2024-08-28
ποΈ
[Product Update] Improved Performance for Reading Numbers and Units in TTS
The functionality has been improved so that all AI voices in Korean can properly pronounce numbers and units.If some sentences are not read correctly, you can c...
Junwoo
2024-08-27
π€
UX Details to Make All TTS Engines Properly Read Korean
VideoStew offers a variety of AI voices. From Google Wavenet, Amazon Polly, KT AI Voice, Naver Clova, Azure, to ElevenLabs...As a result, a natural issue arises...
Junwoo
2024-08-27
π
Short-Form Video Channel Management Strategies for E-commerce Businesses (YouTube Shopping, Naver Short Clips, Coupang Shorts)
The New Challenge in Digital Commerce Marketing: Short-Form VideosRecently, many companies are struggling to attract new customers. This is a significant issue,...
Junwoo
2024-08-22
ποΈ
[Product Update] New Feature: View Detailed Music Copyright Information
All the music provided by VideoStew can be distributed across multiple channels without any copyright worries.For YouTube, if you register your YouTube channel ...
Junwoo
2024-08-06
π
Video Content Strategy to Conquer Naver Short Clips and Coupang Shorts at Once
These days, many people are taking an interest in and challenging themselves with short clips on Naver Shopping Live and Coupang Shorts.In this post, we will di...
Junwoo
2024-08-06
π€
Practical GPT Utilization for Startup Marketers (We said GPT, but we only used Claude π
)
Hello, this is Jun from VideoStew.Lately, I've been writing a lot of behind-the-scenes posts. In this post, I will summarize how I, as a non-developer at a star...
Junwoo
2024-07-22
VideoStew offers a variety of AI voices. From Google Wavenet, Amazon Polly, KT AI Voice, Naver Clova, Azure, to ElevenLabs...
As a result, a natural issue arises: each model is trained differently, so even the same sentence is read slightly differently. This difference is particularly noticeable when reading units.
In this post, weβll discuss the considerations we took into account to ensure proper reading of units in Korean when generating TTS.
Getting Measurement Units Right
When using various TTS engines, we encountered an issue where even the expression "100kg" was read differently by each engine. Some would read it as "hundred K-G," while others would trail off awkwardly at the end with "hundred krr..." (
Yes, even AI can get flustered...)Of course, there were engines that read it accurately as "hundred kilograms."
To address this, we developed a preprocessing library to standardize how these units are read across all engines.
Getting Numbers Right
Running this service, we encountered another unexpected issue. (Korean is truly a fascinating language..)
In Korean, there are two ways to read numbers, something we instinctively use but might not notice.
For instance, when telling time, "10μ 10λΆ" is read as "yeol si sip bun." Why...?
And while general numbers are read in Sino-Korean ("il, i, sam"), when a quantity unit is added, they are read in native Korean ("han gae, du gae, se gae"). Official measurement units use Sino-Korean. (e.g., 10cm = "sip sen-ti-mi-teo")
Alright, let me give you a number. β90β. How would you read it?
Technically, up to 90 should be read as βninety.β Some of you might have read it as βnine zero.β As numbers get larger, we tend to adopt a more convenient way to read them.
Letβs think about smaller numbers. β9.β Yes, everyone would read this as βnine.β
Following this principle, we developed a preprocessing system that reads numbers from 1 to 99 in their unique word forms. However, this is just a guideline, and weβre open to changing it based on customer feedback. For instance, βfortyβ might feel more natural than βfour zero.β
Anyway, to ensure a consistent user experience, we created a unit library corresponding to the unique word forms like βone, two, three.β
If you're looking to implement a TTS service, this library could be useful. However, keep in mind that it's not a complete version as we continuously discover unexpected units through customer feedback.
Detail in UX = Success in SaaS
Encountering the term βquantifierβ for the first time, we faced many challenges while providing a video editing SaaS solution in Korea. It was yet another reminder of how dynamic and remarkable the Korean language isβ¦
While we sometimes envy English-speaking services, they surely have their own set of challenges.
Of course, VideoStew offers a feature called [Manual Text Designation]. This allows you to generate TTS regardless of what's displayed on the screen.
< Setting the sound to be read by TTS regardless of the subtitles displayed on the screen >
By using this method, you can write as you like and as it sounds, leading TTS to pronounce more naturally and allowing users to correct any misread units directly.
The reason we focus on such details is our conviction that these small differences determine the growth of the service.
Users have a preconceived notion of how a sentence with numerical expressions should be read the moment they input it. If it doesn't generate as expected, that's an initial problem. Our ultimate UX goal is to produce the expected result as quickly as possible without additional editing.
We will continue to post our UX considerations like this in the future. As mentioned earlier, in the current situation where all services are leveling up, we believe that pondering over such details determines the success or failure of a service.