Welcome to the Typecast API Documentation!¶
Important
This documentation was updated on Apr 30, 2025.
The Typecast API offers a seamless and versatile solution for integrating advanced voice synthesis into your applications. Our API is designed for simplicity and flexibility, providing you with a wide range of options to bring your digital interactions to life.
Key Features of Typecast API:
Diverse Voice Options: Choose from a wide range of unique voice characters, easily customizable via our web console to fit your specific needs.
Advanced Speech Synthesis: Incorporate emotions and fine-tuned control over speech nuances.
Flexible Integration: Utilize our API through polling or webhooks methods.
Comprehensive Documentation: Benefit from detailed guides and references, with continuous updates and additions of new examples.
Responsive Support: Our team is dedicated to providing timely and helpful support for your queries and feedback.
Start exploring the capabilities of Typecast API and transform your application’s user experience with lifelike, customizable voice interactions.
Basic guide¶
This is the most basic guide to using POST /api/speak
to send a speech synthesis request and receive results.
Currently, there are two ways to use it: polling and webhooks.
Advanced speech synthesis¶
Guide to using POST /api/speak
for more complex usage, such as expressing emotions or controlling the length of the speech.
- Advanced speech synthesis
- Choose a model version
- Apply predefined emotion in your script
- Apply custom emotion in your script
- To limit the maximum length of audio file
- To speak for a fixed duration of time
- Adjust the pitch at the end of a sentence.
- Text-to-Speech: Replicating an existing voice file.
- [SSFM only] Predefined style of speaking
API References¶
Reference documentation for the full API, including getting a list of characters integrated to your API, registering a Webhook URL, and more.
- API References
- Request
- Response
- Error Response
- POST /api/speak
- GET /api/speak/v2/{ :id }
- POST /api/text-to-speech
- GET /api/actor
- GET /api/actor/{ :id }/versions
- GET /api/actor/{ :id }/versions/{ :version }
- GET /api/me
- PUT /api/me/callback-url
- POST /api/speak/resource
- POST /api/speak/prosody-meta/{ :id }
- (deprecated) GET /api/speak/{ :id }