██████╗ ███████╗███╗ ██╗██╗███████╗
██╔════╝ ██╔════╝████╗ ██║██║██╔════╝
██║ ███╗█████╗ ██╔██╗ ██║██║█████╗ 
██║ ██║██╔══╝ ██║╚██╗██║██║██╔══╝ 
╚██████╔╝███████╗██║ ╚████║██║███████╗
 ╚═════╝ ╚══════╝╚═╝ ╚═══╝╚═╝╚══════╝

Experience near-instantaneous speech synthesis on your CPU

简体中文 | English

🎬 Demo Video

🚀 Performance Advantages

🏁 QuickStart

📦 Installation

pip install genie-tts

📥 Pretrained Models

import os
# Set the path to your manually downloaded resource files
# Note: Do this BEFORE importing genie_tts
os.environ["GENIE_DATA_DIR"] = r"C:\path\to\your\GenieData"
import genie_tts as genie
# The library will now load resources from the specified directory

⚡️ Quick Tryout

import genie_tts as genie
import time
# Automatically downloads required files on first run
genie.load_predefined_character('mika')
genie.tts(
 character_name='mika',
 text='どうしようかな......やっぱりやりたいかも......!',
 play=True, # Play the generated audio directly
)
genie.wait_for_playback_done() # Ensure audio playback completes

🎤 TTS Best Practices

import genie_tts as genie
# Step 1: Load character voice model
genie.load_character(
 character_name='<CHARACTER_NAME>', # Replace with your character name
 onnx_model_dir=r"<PATH_TO_CHARACTER_ONNX_MODEL_DIR>", # Folder containing ONNX model
 language='<LANGUAGE_CODE>', # Replace with language code, e.g., 'en', 'zh', 'jp'
 runtime_config={
 "providers": ["CPUExecutionProvider"],
 # Optimal thread count on Apple Silicon (10-core): 4 threads gives ~3x speedup
 # vs single-threaded; beyond 4 threads, scheduling overhead reduces gains.
 # Tune this to your physical core count — typically floor(cores / 2) to cores.
 "intra_op_num_threads": 4,
 "inter_op_num_threads": 1,
 # You can also set defaults via environment variables and keep your code unchanged:
 # GENIE_ORT_PROVIDERS=CPUExecutionProvider
 # GENIE_ORT_INTRA_OP_NUM_THREADS=4
 # GENIE_ORT_INTER_OP_NUM_THREADS=1
 # GENIE_ORT_EXECUTION_MODE=ORT_SEQUENTIAL
 # Explicit runtime_config values override environment variables.
 # Example for CUDA (Linux/Windows with CUDA-enabled onnxruntime):
 # "providers": ["CUDAExecutionProvider", "CPUExecutionProvider"],
 # "provider_options": {"CUDAExecutionProvider": {"device_id": "0"}},
 # Example for Apple Silicon Mac (CoreML — GPU / Neural Engine):
 # "providers": ["CoreMLExecutionProvider", "CPUExecutionProvider"],
 # Note: CoreML is NOT recommended for TTS — the autoregressive T2S decoder
 # calls the ONNX session hundreds of times per sentence, and CoreML's
 # per-call GPU kernel overhead makes it 4-8x slower than CPU for this workload.
 },
)
# Step 2: Set reference audio (for emotion and intonation cloning)
genie.set_reference_audio(
 character_name='<CHARACTER_NAME>', # Must match loaded character name
 audio_path=r"<PATH_TO_REFERENCE_AUDIO>", # Path to reference audio
 audio_text="<REFERENCE_AUDIO_TEXT>", # Corresponding text
)
# Step 3: Run TTS inference and generate audio
genie.tts(
 character_name='<CHARACTER_NAME>', # Must match loaded character
 text="<TEXT_TO_SYNTHESIZE>", # Text to synthesize
 play=True, # Play audio directly
 save_path="<OUTPUT_AUDIO_PATH>", # Output audio file path
)
genie.wait_for_playback_done() # Ensure audio playback completes
print("🎉 Audio generation complete!")

🔧 Model Conversion

pip install torch

import genie_tts as genie
genie.convert_to_onnx(
 torch_pth_path=r"<YOUR .PTH MODEL FILE>", # Replace with your .pth file
 torch_ckpt_path=r"<YOUR .CKPT CHECKPOINT FILE>", # Replace with your .ckpt file
 output_dir=r"<ONNX MODEL OUTPUT DIRECTORY>" # Directory to save ONNX model
)

🌐 Launch FastAPI Server

import genie_tts as genie
# Start server
genie.start_server(
 host="0.0.0.0", # Host address
 port=8000, # Port
 workers=4, # Number of workers for process-based scaling
)
# Single-process mode with bounded queueing (workers=1)
# genie.start_server(
# host="0.0.0.0",
# port=8000,
# workers=1,
# max_concurrency=1,
# queue_maxsize=8,
# )

export GENIE_WORKERS=4
export GENIE_MAX_CONCURRENCY=1
export GENIE_QUEUE_MAXSIZE=8

📝 Roadmap