Speech GenerationGenerate natural and fluent speech using Qwen-TTS models, with multiple parameter adjustments to meet different scenario needs
Voice CloningClone voices from reference audio to create personalized speech output, making voices more distinctive
Voice DesignCreate custom voices based on text descriptions, obtaining ideal sound effects through simple text descriptions
Audio ManagementBuilt-in audio browser for easy management and playback of generated audio files, keeping files organized
Multi-language SupportSupport for both English and Chinese interfaces, meeting the needs of different users and providing localized experience
