fcjr/ltts
Quick CLI for local text-to-speech using Qwen3-TTS or Kokoro TTS.
Supports dual backends with distinct strengths: Qwen3-TTS offers multilingual synthesis (10 languages) with voice cloning and emotional control via instruction prompts, while Kokoro TTS provides lightweight inference with 50+ voices and optional streaming for lower latency. Automatically downloads models to HuggingFace cache and supports CPU/GPU/Apple Silicon inference with multiple audio output formats (MP3, WAV, OGG, FLAC). Integrates stdin piping for pipeline workflows and system audio playback via PulseAudio/PipeWire.
Available on PyPI.
Stars
8
Forks
—
Language
Python
License
MIT
Category
Last pushed
Mar 12, 2026
Monthly downloads
209
Commits (30d)
0
Dependencies
8
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/fcjr/ltts"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
BoltzmannEntropy/MimikaStudio
MimikaStudio - A local-first application for macOS (Apple Silicon) + Agentic MCP Support
aahl/qwen-asr2api
🎤 Qwen 3 ASR to OpenAI API, 免费STT语音识别模型
zhao-kun/VibeVoiceFusion
VibeVoiceFusion is a full-stack, multi-speaker voice generation web system featuring LoRA...
gabriele-mastrapasqua/qwen3-tts
Pure C inference engine for Qwen3-TTS text-to-speech. No Python, no PyTorch — just C and BLAS....
aahl/qwen-tts2api
🗣️ Qwen TTS to OpenAI Speech API