SDK connection types for Alibaba Cloud Intelligent Speech Interaction-Intelligent Speech Interaction(ISI)-阿里云帮助中心

The Alibaba Cloud Intelligent Speech Interaction SDK provides multiple connection types, such as RESTful API, mobile, server-side, WeChat mini program, and WebSocket. These connection types help you quickly and easily integrate speech recognition or speech synthesis features into your services.

SDK Integration

Type	Connection type	Service capabilities
RESTful API	RESTful API	Short sentence recognition, Audio file recognition, Audio file recognition (off-peak), Speech synthesis, Long text-to-speech
Mobile	Mobile iOS SDK	Short sentence recognition, Real-time speech recognition, Express audio file recognition, Speech synthesis
	Mobile Android SDK	Short sentence recognition, Real-time speech recognition, Express audio file recognition, Speech synthesis
	Mobile HarmonyOS Next SDK	Short sentence recognition, Real-time speech recognition, Express audio file recognition, Speech synthesis, Long text-to-speech
	Offline mobile iOS SDK	Offline speech synthesis
	Offline mobile Android SDK	Offline speech synthesis
Server-side	Java SDK	Short sentence recognition, Real-time speech recognition, Audio file recognition, Audio file recognition (off-peak), Speech synthesis, Long text-to-speech, Sound event detection, Speaker recognition, Gender recognition, Language identification
	Python SDK	Short sentence recognition, Real-time speech recognition, Audio file recognition, Audio file recognition (off-peak), Speech synthesis
	C++ SDK	Short sentence recognition, Real-time speech recognition, Speech synthesis
	Go SDK	Short sentence recognition, Real-time speech recognition, Speech synthesis
	Node.js SDK	Short sentence recognition, Real-time speech recognition, Speech synthesis
Mini program	WeChat mini program	Short sentence recognition, Real-time speech recognition, Speech synthesis
WebSocket	WebSocket	Real-time speech recognition

Important

The following services are available only in the commercial edition and do not support free trial: long text speech synthesis, audio file recognition (off-peak), audio file recognition (express), streaming text-to-speech (CosyVoice), and VoiceChat. Calling these services with the free trial returns error code 40000010 (Gateway:FREE_TRIAL_EXPIRED). Go to the Service Management page and upgrade the required services to the commercial edition.