AidVoice SDK

Introduction

The AidVoice SDK is an AI inference SDK specifically designed for voice-related models launched by Athinkra. It aims to simplify the development of core voice processing functions based on edge AI technology, allowing developers to integrate them flexibly and quickly into intelligent applications. The SDK provides a unified and efficient API, supporting industry-leading voice processing AI models to meet the requirements of various business scenarios.

Support Matrix

Operating System Support

	Linux	Android
C++	✅	／
Python	🚧	／
Java	／	✅

ASR Model Support

Whisper-Base-en	SenseVoiceSmall	Whisper Other Versions
✅	✅	🚧

TTS Model Support

MeloTTS-Chinese	MeloTTS-English
✅	✅

✅: Supported 🚧: Planned

Quick Start

Installation

Linux

# Install AidLite QNN version 2.36
sudo aid-pkg update
sudo aid-pkg install aidlite-sdk
sudo aid-pkg install aidlite-qnn236

# Install AidVoice SDK
sudo aid-pkg -i aidvoice-sdk

Android

To be released

Development Workflow

ASR

TTS

Examples

ASR: Identifying Audio Files in QCS8550 Linux System

Install AidVoice SDK

# Install AidLite QNN version 2.36
sudo aid-pkg update
sudo aid-pkg install aidlite-sdk
sudo aid-pkg install aidlite-qnn236

# Install AidVoice SDK
sudo aid-pkg -i aidvoice-sdk

Compile Test Code

# Copy test code
cp -r /usr/local/share/aidvoice/examples /home/aidlux/aidvoice

# Compile
cd /home/aidlux/aidvoice/asr/cpp/
mkdir -p build && cd build
cmake ..
make

Run Example

Tutorial

./test_asr

NOTE

The example uses Whisper by default. To switch to SenseVoiceSmall, please modify the code in test_asr.cpp from cfg.model_type = ModelType::TYPE_WHISPER; to cfg.model_type = ModelType::TYPE_SENSEVOICE;.

TTS: Text-to-Speech in QCS8550 Linux System

Install AidVoice SDK

# Install AidLite QNN version 2.36
sudo aid-pkg update
sudo aid-pkg install aidlite-sdk
sudo aid-pkg install aidlite-qnn236

# Install AidVoice SDK
sudo aid-pkg -i aidvoice-sdk

Compile Test Code

# Copy test code
cp -r /usr/local/share/aidvoice/examples /home/aidlux/aidvoice

# Compile
cd /home/aidlux/aidvoice/tts/cpp/
mkdir -p build && cd build
cmake ..
make

Run Example

cd /home/aidlux/aidvoice/tts/cpp/build
./test_tts

The audio file will be generated in the current directory.

TIP

The example uses MeloTTS-English by default. To switch to MeloTTS-Chinese, please modify the following line in the test_tts.cpp code (Note: the original text incorrectly referred to test_asr.cpp): cfg.model_type = ModelType::TYPE_MELOTTS_ENGLISH; -> cfg.model_type = ModelType::TYPE_MELOTTS_CHINESE;