📢 Supertone API Update
Hello Supertone API users,
A major update to the Supertone API was applied on Thursday, July 31, 2025.
Please review the details below to check if any adjustments are needed for your service.
1. Separation of Preset Voice and Custom Voice
- Preset Voice: Voices created and provided by Supertone
- Custom Voice: Voices registered and managed by the customer
Previously, the /v1/voices
endpoint only supported listing and searching.
With this update, the new /v1/custom-voices
endpoint supports registration, retrieval, searching, and editing.
Additionally, cloned voices that were registered via Supertone Play can now be fully managed through /v1/custom-voices
.
>> No impact on other requests such as Text-to-Speech, Predict Duration.
>> For backward compatibility,/v1/voices
will continue to list and search Custom Voices until 31 August 2025.
2. Voice Cloning Registration via API
You will be able to register new Voice Clones directly through the API, not only through Supertone Play.
3. Streaming TTS (Beta)
A Streaming TTS API will be released in beta, enabling low‑latency audio generation for real‑time services such as AI chatbots and character‑chat applications.
With streaming, you can start receiving audio almost immediately instead of waiting for the entire text to be synthesized.
Thank you for using Supertone.
Getting Started
This documentation is a guide prepared for those who are new to the Supertone API. It’s structured to help you quickly learn the overall flow of generating voices, searching for voices, and managing usage through the API. Supertone API is an integrated service with Supertone Play, allowing you to register voices, recharge credits, and perform voice synthesis all with a single account. It’s designed to be easily accessible not only for developers familiar with APIs, but also for users who operate services primarily through Play.Check Guides
Before integrating the Supertone API, please check the guides in the following order.Quick Start
Voice Selection Guide
voice_id
, how to find voices, and Play integration