Plugin runtime media helpers

// Standard TTS
const clip = await api.runtime.tts.textToSpeech({
  text: "Hello from OpenClaw",
  cfg: api.config,
});

// Telephony-optimized TTS
const telephonyClip = await api.runtime.tts.textToSpeechTelephony({
  text: "Hello from OpenClaw",
  cfg: api.config,
});

// List available voices
const voices = await api.runtime.tts.listVoices({
  provider: "elevenlabs",
  cfg: api.config,
});

// Describe an image
const image = await api.runtime.mediaUnderstanding.describeImageFile({
  filePath: "/tmp/inbound-photo.jpg",
  cfg: api.config,
  agentDir: "/tmp/agent",
});

// Prepare a capture limit before installing audio receive listeners.
const budget = await api.runtime.mediaUnderstanding.resolveAudioInputBudget({
  cfg: api.config,
});
// budget.enabled is false when audio understanding is disabled. Otherwise,
// budget.maxBytes includes the container header and covers the largest fallback.

// Transcribe audio
const { text } = await api.runtime.mediaUnderstanding.transcribeAudioFile({
  filePath: "/tmp/inbound-audio.ogg",
  cfg: api.config,
  mime: "audio/ogg", // optional, for when MIME cannot be inferred
});

// Describe a video
const video = await api.runtime.mediaUnderstanding.describeVideoFile({
  filePath: "/tmp/inbound-video.mp4",
  cfg: api.config,
});

// Generic file analysis
const result = await api.runtime.mediaUnderstanding.runFile({
  filePath: "/tmp/inbound-file.pdf",
  cfg: api.config,
});

// Structured image extraction through a specific provider/model.
// Include at least one image; text inputs are supplemental context.
const evidence = await api.runtime.mediaUnderstanding.extractStructuredWithModel({
  provider: "codex",
  model: "gpt-5.6-sol",
  input: [
    {
      type: "image",
      buffer: receiptImageBuffer,
      fileName: "receipt.png",
      mime: "image/png",
    },
    { type: "text", text: "Prefer the printed total over handwritten notes." },
  ],
  instructions: "Extract vendor, total, and searchable tags.",
  schemaName: "receipt.evidence",
  jsonSchema: {
    type: "object",
    properties: {
      vendor: { type: "string" },
      total: { type: "number" },
      tags: { type: "array", items: { type: "string" } },
    },
    required: ["vendor", "total"],
  },
  cfg: api.config,
});

const result = await api.runtime.imageGeneration.generate({
  prompt: "A robot painting a sunset",
  cfg: api.config,
});

const providers = api.runtime.imageGeneration.listProviders({ cfg: api.config });

const result = await api.runtime.videoGeneration.generate({
  prompt: "A drone shot flying over a coastline at sunrise",
  cfg: api.config,
});

const providers = api.runtime.videoGeneration.listProviders({ cfg: api.config });

const result = await api.runtime.musicGeneration.generate({
  prompt: "An upbeat lo-fi track for a coding session",
  cfg: api.config,
});

const providers = api.runtime.musicGeneration.listProviders({ cfg: api.config });

const providers = api.runtime.webSearch.listProviders({ config: api.config });

const result = await api.runtime.webSearch.search({
  config: api.config,
  args: { query: "OpenClaw plugin SDK", count: 5 },
});

const webMedia = await api.runtime.media.loadWebMedia(url);
const mime = await api.runtime.media.detectMime(buffer);
const kind = api.runtime.media.mediaKindFromMime("image/jpeg"); // "image"
const isVoice = api.runtime.media.isVoiceCompatibleAudio(filePath);
const metadata = await api.runtime.media.getImageMetadata(filePath);
const resized = await api.runtime.media.resizeToJpeg(buffer, { maxWidth: 800 });
const terminalQr = await api.runtime.media.renderQrTerminal("https://openclaw.ai");
const pngQr = await api.runtime.media.renderQrPngBase64("https://openclaw.ai", {
  scale: 6, // 1-12
  marginModules: 4, // 0-16
});
const pngQrDataUrl = await api.runtime.media.renderQrPngDataUrl("https://openclaw.ai");
const tmpRoot = resolvePreferredOpenClawTmpDir();
const pngQrFile = await api.runtime.media.writeQrPngTempFile("https://openclaw.ai", {
  tmpRoot,
  dirPrefix: "my-plugin-qr-",
  fileName: "qr.png",
});