### Set up environment with pip and run inference

Source: https://github.com/misolabsai/misotts/blob/main/README.md

Sets up a Python virtual environment using pip, activates it, installs the MisoTTS package in editable mode, and runs the inference script.

```bash
python3.10 -m venv .venv
source .venv/bin/activate
pip install -e .
python run_misotts.py
```

--------------------------------

### Install uv package manager

Source: https://github.com/misolabsai/misotts/blob/main/README.md

Installs the uv package manager using a curl command. This is a prerequisite for managing Python environments and dependencies.

```bash
curl -LsSf https://astral.sh/uv/install.sh | sh
```

--------------------------------

### Prompted generation for voice cloning

Source: https://github.com/misolabsai/misotts/blob/main/README.md

Python example demonstrating how to use Miso TTS for voice cloning by conditioning generation on prior audio context. Requires torchaudio and the Segment class.

```python
import torchaudio

from generator import Segment, load_miso_8b

generator = load_miso_8b(device="cuda")

prompt_audio, sample_rate = torchaudio.load("prompt.wav")
prompt_audio = torchaudio.functional.resample(
    prompt_audio.squeeze(0),
    orig_freq=sample_rate,
    new_freq=generator.sample_rate,
)

context = [
    Segment(
        speaker=0,
        text="This is the transcript for the prompt audio.",
        audio=prompt_audio,
    )
]

audio = generator.generate(
    text="This is the next sentence to synthesize.",
    speaker=0,
    context=context,
    max_audio_length_ms=10_000,
)
```

--------------------------------

### Generate speech with Miso TTS 8B

Source: https://github.com/misolabsai/misotts/blob/main/README.md

Basic Python example to load the Miso TTS 8B model and generate speech from text. It saves the output audio to 'miso.wav'. Requires PyTorch and torchaudio.

```python
import torch
import torchaudio

from generator import load_miso_8b

device = "cuda" if torch.cuda.is_available() else "cpu"

generator = load_miso_8b(
    device=device,
    model_path_or_repo_id="MisoLabs/MisoTTS",
)

audio = generator.generate(
    text="Hello from Miso.",
    speaker=0,
    context=[],
    max_audio_length_ms=10_000,
)

torchaudio.save("miso.wav", audio.unsqueeze(0).cpu(), generator.sample_rate)
```

--------------------------------

### Clone repository and set up environment with uv

Source: https://github.com/misolabsai/misotts/blob/main/README.md

Clones the MisoTTS repository, synchronizes Python dependencies using uv, and activates the virtual environment. Assumes Python 3.10 is available.

```bash
git clone https://github.com/MisoLabsAI/MisoTTS.git
cd MisoTTS
uv sync --python 3.10
source .venv/bin/activate
```

--------------------------------

### Run Miso TTS inference script

Source: https://github.com/misolabsai/misotts/blob/main/README.md

Executes the main inference script for Miso TTS. This command loads the public model from Hugging Face and saves the output to full_conversation.wav.

```bash
uv run python run_misotts.py
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.