Skip to content

Releases: CodeWithKyrian/whisper.php

v1.10 pre release

14 Dec 16:47
Compare
Choose a tag to compare
v1.10 pre release Pre-release
Pre-release

What's Changed

New Contributors

Full Changelog: 1.0.0...1.1.0

Whisper.php v1.0.0

29 Nov 10:55
Compare
Choose a tag to compare

Initial release of Whisper.php: Native Speech-to-Text for PHP!

This release brings the power of OpenAI's Whisper through whisper.cpp to PHP with ease, enabling fully local and API-free transcription directly in your projects.

🌟 Features:

  • High and Low-Level APIs: Effortlessly transcribe audio or take full control with customizable configurations.

  • Model Auto-Downloading: No manual setup—models download automatically as needed (starting from just 32MB!).

  • Audio Format Support: Compatible with MP3, WAV, OGG, and M4A formats.

  • Output Formats: Export transcriptions to TXT, SRT, VTT, or CSV.

  • Streaming and Progress Callbacks: Get real-time transcription updates and track progress easily.

📦 Installation:

Install with Composer:

composer require codewithkyrian/whisper.php  

💻 Requirements:

  • PHP 8.1+
  • Supported OS:
    • ✅ Linux
    • ✅ macOS
    • 🚧 Windows (coming soon!)

🚀 Getting Started:

Start transcribing in seconds:

use Codewithkyrian\Whisper\Whisper;  

$whisper = Whisper::fromPretrained('tiny.en');  
$segments = $whisper->transcribe('audio.wav');  

foreach ($segments as $segment) {  
    printf("[%s - %s]: %s\n", $segment->startTimestamp, $segment->endTimestamp, $segment->text);
}  

🛠️ Notes:

  • This is the first release and follows whisper.cpp’s versioning with a .0 suffix for PHP-specific updates.
  • Contributions and feedback are welcome!