What is the Text-to-Speech (TTS) API?
The Text-to-Speech (TTS) API converts text into speech audio data. By combining it with the Xoxzo Voice API, you can automatically generate voice messages or spoken notifications.
HelpDesk A
Last Update vor 7 Monaten
Overview
The Text-to-Speech (TTS) API converts text into speech audio data.
By combining it with the Xoxzo SMS or Voice API, you can automatically generate voice messages or spoken notifications.
It supports both Japanese and English voices with clear, natural pronunciation.
Key Features
Convert plain text into an audio file
Supports both Japanese (ja) and English (en)
Can be used in Voice API calls for playback or DIN
Example Use Cases
Play voice messages automatically on incoming calls
Add voice notifications alongside SMS alerts
Build voice assistants or automated call flows
Request and Response Examples
For detailed usage instructions, please refer to the documentation:
👉 Text-to-Speech API Documentation
Notes
Supported languages: Japanese (ja) and English (en).
The input text must be provided in UTF-8 encoding.
The maximum text length is 250 characters per request.