Text to Speech Guide
Generate spoken audio from text in a supported model language and download WAV. This is a synthesis tool, not voice cloning.
Generate spoken audio from text in a supported model language and download WAV. This is a synthesis tool, not voice cloning.
How to use
- Enter a short passage and choose its language, speed and quality.
- Generate and play the audio; the first run loads the model and default voice.
- Once the model is ready, select another voice if needed and generate again.
- Listen to the complete result, revise the text if necessary, and download WAV.
Limits and troubleshooting
The Supertonic language menu includes English, Korean, Japanese and Spanish, but not Chinese. A Chinese interface does not add Chinese synthesis support. Initial model and voice downloads can take time. Shorten the text if memory is limited; punctuation helps control pauses. Names, abbreviations and mixed-language passages need review. Output is WAV, not MP3. If loading fails, check access to the model host and try again.
Privacy and initial loading
Your selected input is processed in this browser, without uploading it to an Aiviko processing server. Loading the page, libraries and any required models still uses the network. Cached assets may be evicted; fully offline operation is not guaranteed. See the privacy policy for other site requests.
Related tools
Quick answer and specifications
The core workflow runs in this browser. Check the supported formats, published limits, and any on-demand model download before you start.
- Inputs
- text
- Outputs
- WAV
- Processing
- On this device, in the browser
- Model languages
- 31 languages — see the language selector
- Last verified
The interface language does not determine the model language. Recognition and pronunciation quality vary; check the result.