Select and download mobile SDK
The NUI SDK supports features such as speech recognition, speech synthesis, and wake word detection. Select the appropriate variant for your business requirements and integrate it into your mobile application.
The connection URLs configured in SDK V2.7.3 and earlier do not support the new Model Studio workspace domains (such as wss://{workspaceId}.maas.aliyuncs.com/api-ws/v1/inference). Using these domains causes SDK initialization or connection failures. Use the following legacy general-purpose domains instead:
China (Beijing): wss://dashscope.aliyuncs.com/api-ws/v1/inference
Singapore: wss://dashscope-intl.aliyuncs.com/api-ws/v1/inference
SDK V2.7.4 and later support the new workspace domains.
Select an SDK variant
The following table lists the application IDs of SDK variants and their supported features. Select a variant based on the features you need.
Application ID | Model Studio (DashScope) | Tongyi Tingwu | Intelligent Speech Interaction (NLS) | |||||||||
CosyVoice speech synthesis | Sambert speech synthesis | Fun-ASR speech recognition and recording file recognition | Gummy speech recognition and translation | Qwen-Livetranslate-Realtime real-time audio translation | Qwen-Audio-Realtime real-time speech interaction | Real-time streaming | Speech recognition and recording file recognition | Speech synthesis | On-device speech synthesis | On-device wake word detection | On-device acoustic echo cancellation and voice activity detection | |
01B | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ |
028 | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
029 | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ |
037 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ |
038 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
039 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ |
040 | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ |
047 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | ✅ |
049 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
Latest SDK downloads and release notes
Downloads
Android SDK
Item | Description | ||||||||
Name | Intelligent Speech Interaction SDK for mobile devices | ||||||||
Developer | Alibaba Cloud Computing Co., Ltd. | ||||||||
Version | 2.7.5 | ||||||||
Package name | com.alibaba.idst.nui | ||||||||
Last updated | 2026-10-10 | ||||||||
Application ID | 039 | 038 | 037 | 029 | 028 | 01B | 049 | 047 | 040 |
SDK package MD5 | 61e183ba52bbbf6f9c29e27a32fb8e93 | 0c3d73bcdfcef29a1472dc8068977a2c | c1bd9c2421bc36541811f860b0d8db6f | 6297a772f63d87183aafa911fbd8883e | 1c5db1b4981e20a6801d541690bcf6e8 | b098a449fd93ef4274b09d3a190cbaf7 | 739777fdebcf7a31a3715da5e834f557 | 02991026fdbca0cc5382e8cb3b5fc938 | 4e059dac0ed43f802aaab1e74428b26c |
SDK package download | |||||||||
Renamed SDK package MD5 | 6c60f6d9038166d442dbef460600a26c | fbe0042f835a9cab589bdd166a21f35a | ee3e0f44cae2d56d444eed1a50b57588 | 6b55ad9ca9769f78cd7c847a25cd5acd | e01a2ced2cce1300b3a80b9b1d860bc8 | 3baa755b25078a52527aa156c44753a9 | |||
Renamed SDK package download | |||||||||
Renamed SDK packages: If your project already integrates our SDK, use a renamed SDK package to resolve package conflicts.
Category | Compatibility |
Operating system | Android 5.0 and later (API level 21) |
Architecture | armeabi-v7a, arm64-v8a, x86_64 |
iOS SDK
Item | Description | ||||||||
Name | Intelligent Speech Interaction SDK for mobile devices | ||||||||
Developer | Alibaba Cloud Computing Co., Ltd. | ||||||||
Version | 2.7.5 | ||||||||
Last updated | 2026-10-10 | ||||||||
Application ID | 039 | 038 | 037 | 029 | 028 | 01B | 049 | 047 | 040 |
SDK package MD5 | 881f91817804333bd538317f04612921 | fd7926448f3f8330fa0bee62256924a8 | 1bcc6b1e672ef759df3743e9273b1616 | 644f2f4307e75a681f0b564ffc715506 | f7238aae8b4a84c28126d528c3117566 | abc144429174099ba81e45dd8987d9b8 | f6600a30d3e1e4b8b353ba8929685d8b | 8aa8169d7e943bf51ed9c3e5b446254c | 0cde35571184bc680ee9583ad9b3bd76 |
SDK package download | |||||||||
Renamed SDK package MD5 | c1192a125b0239ff295cf9c9ff598807 | d9da2453a60bc69d43b9a35bd0c9f303 | bb3cd0a35d12e3fc0c35b016f0788fbf | 30b8327b3fa8ec8aea61145626d65d07 | 9d59c687d5fbec6c2a24ac2408245fb2 | 89dec02c405f8af656508255baa03f41 | |||
Renamed SDK package download | |||||||||
Renamed SDK packages: If your project already integrates our SDK, use a renamed SDK package to resolve package conflicts.
Category | Compatibility |
Operating system | iOS 12 and later |
Architecture | arm64-device, arm64-simulator, x86_64-simulator |
HarmonyOS SDK
Item | Description | ||||||
Name | Intelligent Speech Interaction SDK for mobile devices | ||||||
Developer | Alibaba Cloud Computing Co., Ltd. | ||||||
Version | 2.7.4 | ||||||
Last updated | 2026-09-08 | ||||||
Application ID | 01B | 047 | 049 | ||||
SDK package MD5 | e30652b9cb28e992a3b5737af8b709a5 | 447f4418b8f563dba8b507da8486a28b | 61039f0082966b3f774ed556c7f75652 | ||||
SDK package download | |||||||
Release notes
V2.7.5
Improved the ability to resume real-time speech recognition after a network interruption.
Added support for new Qwen-Audio-ASR models.
Fixed an issue that prevented the generic parameter-setting API from taking effect.
V2.7.4
Added support for Qwen-Audio-Realtime real-time speech interaction.
Added support for on-device acoustic echo cancellation (AEC).
The storage path and file name of the authentication certificate for on-device features can now be configured.
Added support for the new Model Studio domains.
V2.7.3
Added real-time audio translation.
Added support for resuming transmission after a network disconnection and for reporting network disconnection errors.
V2.7.2
Fixed bugs.
Added support for FunASR speech recognition after wake word detection and a sample project.
V2.7.1
Fixed bugs.
V2.7.0
Added support for Model Studio speech recognition and speech synthesis.
Added support for decoding Opus and MP3 audio into PCM for speech synthesis.
The wake word callback events EVENT_WUW_START and EVENT_WUW_END now include wake word information.
Added the onNuiAssistEventCallback auxiliary callback, which can return information such as wake word audio data.
Streamlined OpenSSL to reduce the package size.
Fixed intermittent crashes during offline speech synthesis and offline wake word detection.
Previous LTS SDK downloads and release notes
Downloads
2.6.9
Android SDK
V2.6.9-01B-20251009_Android_OpenSSL.tar.gz
MD5:37d68cc718978a8143f619aa32d13c7f
V2.6.9-028-20251009_Android_OpenSSL.tar.gz
MD5:7eafe1b459acaffe6a2d7da569aecefb
V2.6.9-029-20251009_Android_OpenSSL.tar.gz
MD5:a5dcbce584aa284e95955b663bf41ad3
iOS SDK
V2.6.9-01B-20251009_iOS_OpenSSL.tar.gz
MD5:6e8c37e0d2e10de39200c400547e1dad
V2.6.9-028-20251009_iOS_OpenSSL.tar.gz
MD5:77a7d65f46149b9e37e22525b3ee53d3
V2.6.9-029-20251009_iOS_OpenSSL.tar.gz
MD5:0538fa3b47a0edd8775cec6575e23ed2
Release notes
2.6.9
Added x86_64 architecture support to the iOS release build.
Added support for decoding Opus and MP3 audio into PCM for speech synthesis.
Fixed an issue where nui_tts_get_param("error_msg") did not return error information.
Fixed intermittent crashes during offline speech synthesis and offline wake word detection.