Voice Support
Having issues with voice quality, unnatural intonation, or voice parameter settings while using Play?
Let us know through this page!🎧
Your feedback is incredibly valuable and helps us improve the voice experience. We’re always listening to make your experience even better.
📌 Voice Cloning
Q. The pronunciation in the cloned voice isn’t clear.
A. To achieve better TTS quality using voice cloning, please make sure to record in a clean, noise-free environment and read the script with clear and accurate pronunciation.
Q. There is noise in the TTS audio generated with voice cloning.
A. This may occur because background noise was captured together with the voice during the voice cloning recording process.
For better voice quality, we recommend recording in a noise-free studio environment using an external microphone that captures audio clearly. This will result in significantly higher-quality audio output.
Q. The end of the TTS audio generated with voice cloning gets cut off early.
A. This issue can be caused by background noise or suboptimal recording conditions.
When the system misdetects the end of the speech due to noise, the audio may be truncated early.
Using clean, high-quality audio recordings can help reduce this issue.
📌 Record or Import Audio Feature
Q. The audio generated using 'Record or Import Audio' sounds too quiet.
A. Please check your computer settings and increase the microphone input volume if necessary.
Using an external microphone is recommended over a built-in one for clearer and more accurate recording.
If you used the Import Audio function, make sure the original audio file has sufficient volume, and adjust it if needed.
Q. The audio recorded with ‘Record or Import Audio’ sounds unclear.
A. When using the ‘Record or Import Audio’ feature, it is essential to ensure a proper input volume level and a clean, clear recording environment.
Using an external microphone will result in higher-quality output, and we recommend recording in a noise-free environment for the best results.
📌 Voice Parameter Settings
Q. What is the Pitch Shift feature?
A. Pitch Shift allows you to adjust the pitch (highness or lowness) of the voice.
Move the slider to the right for a higher, lighter tone, or to the left for a lower, deeper tone.
If you prefer a bright, cheerful voice, shift to the right. For a calm, low tone, shift to the left.
Q. What is the Pitch Variance feature?
A. Pitch Variance controls the range of pitch variation in the voice.
It determines how much the pitch rises and falls while speaking.
Moving the slider to the right increases variation, making the tone more expressive, dynamic, and sometimes exaggerated.
Moving it to the left reduces variation, resulting in a more monotone, robotic voice with less emotional nuance.
Q. What is the Speed feature?
A. The Speed feature adjusts the playback speed of the generated audio.
Moving the slider to the right will increase the speed, while moving it to the left will slow it down.
📌 Supported Languages for TTS
Q. Which languages are currently supported for TTS generation?
A. Currently, only Korean, English, and Japanese are supported.
TTS generation may not work properly with unsupported languages.
We plan to expand language support in future updates.
For other 1:1 inquiries, providing the following details will help us resolve your issue more quickly and accurately:
-
Your Supertone account email
-
The browser in which the issue occurred (e.g., Chrome, Safari)
-
A screen recording or screenshot showing the issue
-
The voice you used
-
The language selected
-
The style applied
-
The parameter settings
-
The input sentence (for context)