Metadata-Version: 2.4
Name: cykk-audio-transcriber
Version: 0.1.0
Summary: CLI for audio transcription, subtitle export, and optional translation.
Author-email: chenyk <752534707@qq.com>
License-Expression: MIT
Project-URL: Homepage, https://github.com/cykk/audiototext-pypi
Project-URL: Repository, https://github.com/cykk/audiototext-pypi
Project-URL: Issues, https://github.com/cykk/audiototext-pypi/issues
Keywords: transcription,speech-to-text,whisper,audio,subtitles
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Environment :: Console
Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
Requires-Python: >=3.11
Description-Content-Type: text/markdown
License-File: LICENSE
Provides-Extra: local
Requires-Dist: openai-whisper; extra == "local"
Requires-Dist: torch; extra == "local"
Requires-Dist: numpy; extra == "local"
Provides-Extra: api
Requires-Dist: openai>=1.35.0; extra == "api"
Requires-Dist: pydub>=0.25.1; extra == "api"
Provides-Extra: translate
Requires-Dist: deepl>=1.18.0; extra == "translate"
Provides-Extra: all
Requires-Dist: openai-whisper; extra == "all"
Requires-Dist: torch; extra == "all"
Requires-Dist: numpy; extra == "all"
Requires-Dist: openai>=1.35.0; extra == "all"
Requires-Dist: pydub>=0.25.1; extra == "all"
Requires-Dist: deepl>=1.18.0; extra == "all"
Provides-Extra: test
Requires-Dist: pytest>=8.0; extra == "test"
Requires-Dist: build>=1.2.2; extra == "test"
Requires-Dist: twine>=5.1.0; extra == "test"
Dynamic: license-file

# cykk-audio-transcriber

`cykk-audio-transcriber` is a Python command-line package for transcribing audio into plain text, subtitles, and optional translated transcripts.

It supports:

- local Whisper inference
- the OpenAI speech API
- subtitle export in `txt`, `srt`, `vtt`, `tsv`, and `json`
- optional DeepL-based translation

## Installation

Install the local Whisper workflow:

```bash
pip install "cykk-audio-transcriber[local]"
```

Install the OpenAI API workflow:

```bash
pip install "cykk-audio-transcriber[api]"
```

Install everything:

```bash
pip install "cykk-audio-transcriber[all]"
```

## Usage

```bash
audiototext recording.mp3 --model small --output-formats txt,srt
```

```bash
audiototext recording.mp3 --api-key $OPENAI_API_KEY --output-formats txt,vtt
```

## Project

GitHub repository: https://github.com/cykk/audiototext-pypi

## Related options

For a browser-based transcription workflow, see [mp3totext.ai](https://mp3totext.ai/).
For an online audio and video transcription workflow, see [transvio.ai](https://transvio.ai/).
