在 MacBook 上运行的本地语音 AI
四分钟开源库导览:Nemotron Streaming 实时转录、PersonaPlex 本地语音对话,以及 VoxCPM2 48 kHz 语音克隆 —— 所有演示都在本地笔记本上运行。
三大端侧使用场景分组。
每个分组都涵盖多个由 Soniqo 组件拼接而成的子场景。投入音频,即可在本地、实时获得对话、转录或合成语音。
三十多个模型。一个技术栈。
上面的用例流水线全部由这些模型拼接而成。点击组件查看其架构、CLI、Swift API 与基准测试。全部支持 Apple Silicon,多数也支持 Android 与 Linux。
语音转文字
52 langs, RTF 0.06, 4-/8-bit
speech-swift native CoreML baseline
Small, medium, large-v3, and turbo exports
32× real-time on Neural Engine
120M, 25 langs, streaming partials + EOU, ~232 MB on-device
1,672 languages, 300M–7B
Word-level timestamps, 80 ms
Streaming with punctuation
文字转语音
9 langs, zero-shot cloning, bf16 / 8-bit
12 Hz codec LM, faster than real-time
48 kHz, 30 langs, voice design + cloning
Native MLX zero-shot cloning, emotion + tempo controls
99M, 31 langs, 44.1 kHz
CoreML voice cloning, TTFT 0.27s, RTF 0.59
600+ langs, NAR diffusion cloning
Hindi emotion TTS + raw reference cloning
Style markers + zero-shot cloning
54 voices, iOS-ready, 10 langs
90-min podcasts / audiobooks
9 langs, 5 baked voices, streaming
IndexTTS2, CosyVoice, Chatterbox Flash, Qwen3-TTS ICL
音频分析
音乐与音频制作
44.1 kHz stereo, variable-length music
Text → 30 s music, RTF 0.36
Open-Unmix + HTDemucs v4, 4 stems
DeepFilterNet3, 48 kHz real-time
Sidon denoise + dereverb → 48 kHz
48 kHz audio super-resolution
