Vydra Provider: Image, Video, and Speech in OpenClaw

The official Vydra plugin provides:

• Image creation through vydra/grok-imagine
• Video creation through vydra/veo3 (text-to-video) and vydra/kling (image-to-video)
• Speech generation via Vydra's TTS route, which is backed by ElevenLabs

All three capabilities share the same VYDRA_API_KEY within OpenClaw.

Warning

The base URL must be set to https://www.vydra.ai/api/v1. Vydra's apex host (https://vydra.ai/api/v1) currently redirects to www. On that cross-host redirect, some HTTP clients discard Authorization, which changes a valid API key into a confusing auth error. To prevent this, the bundled plugin normalizes any configured vydra.ai base URL to www.vydra.ai.

Setup

Install the plugin

openclaw plugins install @openclaw/vydra-provider
openclaw gateway restart

Run interactive onboarding

openclaw onboard --auth-choice vydra-api-key

Alternatively, set the env var directly:

export VYDRA_API_KEY="vydra_live_..."

Choose a default capability

Choose one or more of the capabilities below (image, video, or speech) and apply the corresponding configuration.

Capabilities

Image generation

Default and only Vydra image model:

• vydra/grok-imagine

Make it the default image provider:

{
  agents: {
    defaults: {
      mediaModels: {
        image: {
          primary: "vydra/grok-imagine",
        },
      },
    },
  },
}

Vydra only supports text-to-image, with a maximum of one image per request. Vydra's hosted edit routes expect remote image URLs, and the plugin does not include a Vydra-specific upload bridge.

Note

Refer to Image Generation for shared tool parameters, provider selection, and failover behavior.

Video generation

Registered video models:

• vydra/veo3 for text-to-video (rejects image reference inputs)
• vydra/kling for image-to-video (requires exactly one remote image URL)

Make Vydra the default video provider:

{
  agents: {
    defaults: {
      mediaModels: {
        video: {
          primary: "vydra/veo3",
        },
      },
    },
  },
}

Notes:

• vydra/kling rejects local file uploads up front; only a remote image URL reference works.
• Vydra's kling HTTP route has been inconsistent about whether it requires image_url or video_url; the plugin sends the same remote image URL in both fields.
• The plugin stays conservative and does not forward undocumented style knobs such as aspect ratio, resolution, watermark, or generated audio.

Note

Refer to Video Generation for shared tool parameters, provider selection, and failover behavior.

Video live tests

Provider-specific live coverage:

OPENCLAW_LIVE_TEST=1 \
OPENCLAW_LIVE_VYDRA_VIDEO=1 \
pnpm test:live -- extensions/vydra/vydra.live.test.ts

The Vydra live file covers:

• vydra/veo3 text-to-video
• vydra/kling image-to-video using a remote image URL

Override the remote image fixture when needed:

export OPENCLAW_LIVE_VYDRA_KLING_IMAGE_URL="https://example.com/reference.png"

Speech synthesis

Make Vydra the speech provider:

{
  tts: {
    provider: "vydra",
    providers: {
      vydra: {
        apiKey: "${VYDRA_API_KEY}",
        voiceId: "21m00Tcm4TlvDq8ikWAM",
      },
    },
  },
}

Defaults:

• Model: elevenlabs/tts
• Voice id: 21m00Tcm4TlvDq8ikWAM ("Rachel")

The plugin exposes this one known-good default voice and returns MP3 audio files.

Related

• Provider directory, Browse all available providers.

• Image generation, Shared image tool parameters and provider selection.

• Video generation, Shared video tool parameters and provider selection.

• Configuration reference, Agent defaults and model configuration.