conda create -n moss-tts-nano python=3.12 -y
conda activate moss-tts-nano

git clone https://github.com/OpenMOSS/MOSS-TTS-Nano.git
cd MOSS-TTS-Nano

pip install -r requirements.txt
pip install -e .

conda install -c conda-forge pynini=2.1.6.post1 -y
pip install git+https://github.com/WhizZest/WeTextProcessing.git

moss-tts-nano generate \
  --prompt-speech assets/audio/zh_1.wav \
  --text "欢迎关注模思智能、上海创智学院与复旦大学自然语言处理实验室。"

moss-tts-nano generate \
  --prompt-speech assets/audio/zh_1.wav \
  --text-file my_script.txt \
  --output output.wav

moss-tts-nano serve
# or directly:
python app.py

python infer.py \
  --prompt-audio-path assets/audio/zh_1.wav \
  --text "Hello, this is a test of MOSS-TTS-Nano."

from infer import MossTTSNanoInference

# Initialize once (downloads weights on first run)
tts = MossTTSNanoInference()

# Voice clone: synthesize text in the style of the reference audio
audio = tts.infer(
    text="欢迎使用MOSS语音合成系统。",
    prompt_audio_path="assets/audio/zh_1.wav",
)

# Save output
import soundfile as sf
sf.write("output.wav", audio, samplerate=48000)

from infer import MossTTSNanoInference

tts = MossTTSNanoInference()

audio = tts.infer(
    text="Welcome to MOSS TTS Nano, a tiny but capable text to speech model.",
    prompt_audio_path="assets/audio/en_sample.wav",
)

import soundfile as sf
sf.write("english_output.wav", audio, samplerate=48000)

from infer import MossTTSNanoInference
import soundfile as sf
import numpy as np

tts = MossTTSNanoInference()

chunks = []
for audio_chunk in tts.infer_stream(
    text="This sentence is generated chunk by chunk for low latency playback.",
    prompt_audio_path="assets/audio/en_sample.wav",
):
    chunks.append(audio_chunk)
    # process or play chunk in real time here

full_audio = np.concatenate(chunks)
sf.write("streamed_output.wav", full_audio, samplerate=48000)

from infer import MossTTSNanoInference

tts = MossTTSNanoInference()

long_text = """
MOSS-TTS-Nano supports long-form synthesis through automatic chunking.
Each chunk uses the same reference voice, producing consistent speaker identity
across the entire output even for multi-paragraph documents.
"""

audio = tts.infer(
    text=long_text,
    prompt_audio_path="assets/audio/en_sample.wav",
)

import soundfile as sf
sf.write("long_form_output.wav", audio, samplerate=48000)

import requests
import base64
import soundfile as sf
import io
import numpy as np

# Read reference audio as base64
with open("assets/audio/zh_1.wav", "rb") as f:
    ref_audio_b64 = base64.b64encode(f.read()).decode()

response = requests.post(
    "http://127.0.0.1:18083/generate",
    json={
        "text": "你好，这是一个语音合成测试。",
        "prompt_audio_base64": ref_audio_b64,
    },
)

data = response.json()
audio_bytes = base64.b64decode(data["audio_base64"])

audio_array, sr = sf.read(io.BytesIO(audio_bytes))
sf.write("api_output.wav", audio_array, samplerate=sr)

import requests

with open("assets/audio/zh_1.wav", "rb") as f:
    ref_audio_b64 = __import__("base64").b64encode(f.read()).decode()

with requests.post(
    "http://127.0.0.1:18083/generate_stream",
    json={
        "text": "流式语音合成示例，适合实时播放场景。",
        "prompt_audio_base64": ref_audio_b64,
    },
    stream=True,
) as resp:
    with open("stream_output.wav", "wb") as out:
        for chunk in resp.iter_content(chunk_size=4096):
            out.write(chunk)

from infer import MossTTSNanoInference
import soundfile as sf

tts = MossTTSNanoInference()
ref = "assets/audio/zh_1.wav"

sentences = [
    "第一句话，用于批量合成测试。",
    "第二句话，保持相同的音色。",
    "第三句话，输出独立的音频文件。",
]

for i, sentence in enumerate(sentences):
    audio = tts.infer(text=sentence, prompt_audio_path=ref)
    sf.write(f"output_{i:02d}.wav", audio, samplerate=48000)
    print(f"Saved output_{i:02d}.wav")

import sounddevice as sd
import numpy as np
from infer import MossTTSNanoInference

tts = MossTTSNanoInference()

buffer = []
for chunk in tts.infer_stream(
    text="Real-time playback example using sounddevice.",
    prompt_audio_path="assets/audio/en_sample.wav",
):
    buffer.append(chunk)

audio = np.concatenate(buffer)
sd.play(audio, samplerate=48000)
sd.wait()

import gradio as gr
import soundfile as sf
import numpy as np
import io
from infer import MossTTSNanoInference

tts = MossTTSNanoInference()

def synthesize(reference_audio_path: str, text: str):
    audio = tts.infer(text=text, prompt_audio_path=reference_audio_path)
    # Return as (sample_rate, numpy_array) tuple for Gradio Audio component
    return (48000, audio)

demo = gr.Interface(
    fn=synthesize,
    inputs=[
        gr.Audio(type="filepath", label="Reference Voice"),
        gr.Textbox(label="Text to synthesize"),
    ],
    outputs=gr.Audio(label="Generated Speech"),
    title="MOSS-TTS-Nano Voice Clone",
)

demo.launch()

# Use conda to get pynini, then install from source
conda install -c conda-forge pynini=2.1.6.post1 -y
pip install git+https://github.com/WhizZest/WeTextProcessing.git

export HF_ENDPOINT=https://hf-mirror.com
python infer.py --prompt-audio-path assets/audio/zh_1.wav --text "测试"

pip install modelscope

# Re-run editable install inside the active conda env
pip install -e .
which moss-tts-nano   # should resolve now

# Default port is 18083; check what occupies it
lsof -i :18083
# Kill if needed, then relaunch
moss-tts-nano serve