manifest / ai / ai-provider-for-deapi

AI Provider for deAPI

deAPI provider for the WordPress AI Client: image and video generation, image editing, text-to-speech and embeddings with open models.

by deAPI · github.com/deapi-ai/ai-provider-for-deapi · website

★ 0stars

Install

Download source zip No release zip yet

This is the repository archive. It installs, but the folder name will carry the branch suffix and updates will not flow.

Install straight from GitHub with WP-CLI:

wp plugin install https://github.com/deapi-ai/ai-provider-for-deapi/archive/refs/heads/main.zip

No built-in updater. New versions won't appear under Dashboard → Updates. Install new releases yourself, or let Git Updater track the repository.

Readme github.com/deapi-ai/ai-provider-for-deapi ↗

deAPI provider for the WordPress AI Client (WordPress 7.0+) and the PHP AI Client SDK.

Once the plugin is active and an API key is saved under Settings > Connectors, any plugin built on the AI Client can use deAPI's open models:

Capability	Models	Notes
Image generation	`Flux1schnell`, `ZImageTurbo_INT8`, `Flux_2_Klein_4B_BF16`, `ZAnimeDistill_8Step_INT8`	PNG; FLUX.1 also landscape and portrait
Image editing	`Flux_2_Klein_4B_BF16`	Up to 3 input images, inline or public URL
Video generation	`Ltx2_5_22B_Dist_INT8`, `MiniMaxH3_33B_Turbo_INT8`	MP4, text-to-video or first-frame image; blocks until the video is ready
Text-to-speech	`Kokoro`, `Chatterbox`, `Qwen3_TTS_12Hz_1_7B_CustomVoice`	MP3; OpenAI voice names work as aliases
Embeddings	`Bge_M3_FP16`	1024 dimensions; needs AI Client 1.4+

deAPI has no chat models, so text features keep using your other providers. Requests go to deAPI's OpenAI-compatible gateway at https://oai.deapi.ai/v1 (docs).

Usage

use WordPress\AiClient\Files\Enums\MediaOrientationEnum;
use WordPress\AiClient\Providers\Models\DTO\ModelConfig;

// Image
$image = wp_ai_client_prompt( 'A red fox in a snowy forest at golden hour' )
    ->using_model_preference( array( 'deapi', 'Flux1schnell' ) )
    ->as_output_media_orientation( MediaOrientationEnum::landscape() )
    ->generate_image();

// Edit: add the source image to the prompt
$edited = wp_ai_client_prompt( 'Make it night with a full moon' )
    ->with_file( $image )
    ->using_model_preference( array( 'deapi', 'Flux_2_Klein_4B_BF16' ) )
    ->generate_image();

// Video (run it from WP-CLI, cron or a background job: it takes 30 s to 2 min)
$video = wp_ai_client_prompt( 'A paper boat drifting down a rain-soaked street' )
    ->using_model_preference( array( 'deapi', 'Ltx2_5_22B_Dist_INT8' ) )
    ->using_model_config( ModelConfig::fromArray( array( 'customOptions' => array( 'seconds' => 5 ) ) ) )
    ->as_output_media_aspect_ratio( '16:9' )
    ->generate_video();

// Speech
$mp3 = wp_ai_client_prompt( 'Hello from deAPI.' )
    ->using_model_preference( array( 'deapi', 'Kokoro' ) )
    ->as_output_speech_voice( 'af_nova' )
    ->convert_text_to_speech();

The API key can also come from the DEAPI_API_KEY environment variable or constant. Get a key at app.deapi.ai.

Development

composer install
vendor/bin/phpunit

The tests mock the HTTP layer and run on PHP 7.4+ against php-ai-client 1.3.1 (bundled with WordPress 7.0 and 7.1) and 1.5.

Releases: bump Version in ai-provider-for-deapi.php and Stable tag in readme.txt, then publish a GitHub release. The deploy workflow pushes it to wordpress.org (it needs the SVN_USERNAME and SVN_PASSWORD secrets).

License

GPL-2.0-or-later. The model classes follow the structure of the AI Provider for OpenAI plugin by the WordPress AI Team (GPL-2.0-or-later).