Metadata-Version: 2.4
Name: podonos
Version: 0.44.0
Summary: Managed evaluation for audio & speech
Author-email: David Anderson <david@podonos.com>
License-Expression: MIT
Project-URL: Homepage, https://www.podonos.com
Project-URL: Repository, https://github.com/podonos/podonos-pysdk
Keywords: ai,speech,synthesis
Classifier: Intended Audience :: Science/Research
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Classifier: Topic :: Multimedia :: Sound/Audio :: Analysis
Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: filetype
Requires-Dist: glog
Requires-Dist: natsort
Requires-Dist: packaging
Requires-Dist: requests<3,>=2.33.0
Requires-Dist: urllib3<3,>=2.7.0
Requires-Dist: soundfile==0.12.1
Requires-Dist: tqdm
Requires-Dist: typing_extensions>=4.0.0
Provides-Extra: dev
Requires-Dist: numpy<2.4.0,>=2.0.0; python_version < "3.14" and extra == "dev"
Requires-Dist: numpy>=2.4.0; python_version >= "3.14" and extra == "dev"
Requires-Dist: pytest; extra == "dev"
Dynamic: license-file

# Podonos

## Quick Start

### 👨‍💻 1. Get an API key

Visit [https://www.podonos.com](https://www.podonos.com), log in or sign up, and get an API key.
For more details, see [Docs](https://www.podonos.com/docs/apikey)

### 💾 2. Install podonos Python package

First of all, make sure you have installed Python 3.10 or newer

```bash
python --version
```

Once you confirm your Python version, install the package:

```bash
pip install podonos
```

### 🎙️ 3. Start speech evaluation

```python
import podonos
from podonos import *

client = podonos.init(api_key="<YOUR_API_KEY_HERE>")
etor = client.create_evaluator()
for i in script_list:
  gen_audio = my_model.generate_and_save(i, script_list[i], f'/a/b/{i}.wav')
  etor.add_file(file=File(path=f'/a/b/{i}.wav', model_tag="my_new_model",
                          tags=["syn1", "male", "American"]))
etor.close()
```

Once we evaluate the audio files, we will email you the evaluation report within 12 hours.

For comparative evaluations (`add_files`), you do not need to shuffle the models yourself. Podonos
randomizes the presentation order per participant, and the SDK normalizes what it stores, so the
same model always keeps the same position across groups. See
[Bias minimization](https://www.podonos.com/docs/reliability/bias-minimization).

One positional rule remains: for `CSMOS`, the reference must be passed last (`file2`).

## 👌 How to run the code testing

Run this at the base directory:

```bash
pytest
```

## 📗 Documentation

For a deeper dive on all capabilities and details, please refer to [Documentation](https://www.podonos.com/docs).

## 📑 License

[MIT License](https://github.com/podonos/podonos-pysdk/blob/main/LICENSE)
