本地语音

Local STT and TTS on macOS using native Apple capabilities. Speech-to-text via yap (Apple Speech.framework), text-to-speech via say + ffmpeg. Fully offline, no API keys required. Includes voice quality detection and smart voice selection.

Local speech-to-text using Vosk. Lightweight, fast, fully offline. Perfect for transcribing Telegram voice messages, audio files, or any speech-to-text task without cloud APIs.

Text-to-speech using Kokoro local TTS. Use when the user wants to convert text to audio, read aloud, or generate speech.

Free local speech-to-text for Telegram and WhatsApp using MLX Whisper on Apple Silicon. Private, no API costs.

Text-to-speech using Kokoro local TTS. Use when the user wants to convert text to audio, read aloud, or generate speech.

Text-to-Speech using SiliconFlow API (CosyVoice2). Supports multiple voices, languages, and dialects.