@pipedream/palatine_speech 0.0.1 → 0.1.0

package/actions/download-transcription/download-transcription.mjs

@@ -0,0 +1,65 @@
+import fs from "fs";
+import path from "path";
+import app from "../../palatine_speech.app.mjs";
+
+export default {
+  key: "palatine_speech-download-transcription",
+  name: "Download Transcription",
+  description: "Downloads the transcription results in a specified file format (SRT, VTT, TXT, CSV, or XLSX). The task must be completed before downloading. [See the documentation](https://docs.speech.palatine.ru/api-reference/transcribe/transcribe-polling-api/download-as-file)",
+  version: "0.0.1",
+  type: "action",
+  annotations: {
+    readOnlyHint: false,
+    destructiveHint: false,
+    openWorldHint: true,
+  },
+  props: {
+    app,
+    taskId: {
+      propDefinition: [
+        app,
+        "taskId",
+      ],
+    },
+    fileFormat: {
+      propDefinition: [
+        app,
+        "fileFormat",
+      ],
+    },
+    filename: {
+      type: "string",
+      label: "Filename",
+      description: "The name of the file to save the transcription to in the `/tmp` directory",
+    },
+    syncDir: {
+      type: "dir",
+      accessMode: "write",
+      sync: true,
+    },
+  },
+  async run({ $ }) {
+    const {
+      app,
+      taskId,
+      fileFormat,
+      filename,
+    } = this;
+
+    const response = await app.downloadTranscription({
+      $,
+      taskId,
+      params: {
+        file_format: fileFormat,
+      },
+    });
+
+    const filePath = path.join("/tmp", path.basename(filename));
+    fs.writeFileSync(filePath, response);
+
+    $.export("$summary", `Successfully downloaded transcription to ${filePath}`);
+    return {
+      filePath,
+    };
+  },
+};

package/actions/get-task-status/get-task-status.mjs

@@ -0,0 +1,47 @@
+import app from "../../palatine_speech.app.mjs";
+
+export default {
+  key: "palatine_speech-get-task-status",
+  name: "Get Task Status",
+  description: "Retrieves the status and results of a transcription task. Use this to poll for completion after starting a transcription job. [See the documentation](https://docs.speech.palatine.ru/api-reference/transcribe/transcribe-polling-api/task-status)",
+  version: "0.0.1",
+  type: "action",
+  annotations: {
+    readOnlyHint: true,
+    destructiveHint: false,
+    openWorldHint: true,
+  },
+  props: {
+    app,
+    taskId: {
+      propDefinition: [
+        app,
+        "taskId",
+      ],
+    },
+    responseFormat: {
+      propDefinition: [
+        app,
+        "responseFormat",
+      ],
+    },
+  },
+  async run({ $ }) {
+    const {
+      app,
+      taskId,
+      responseFormat,
+    } = this;
+
+    const response = await app.getTaskStatus({
+      $,
+      taskId,
+      params: {
+        response_format: responseFormat,
+      },
+    });
+
+    $.export("$summary", `Successfully retrieved task status as \`${response.status}\`.`);
+    return response;
+  },
+};

package/actions/mark-task-done/mark-task-done.mjs

@@ -0,0 +1,37 @@
+import app from "../../palatine_speech.app.mjs";
+
+export default {
+  key: "palatine_speech-mark-task-done",
+  name: "Mark Task Done",
+  description: "Marks a transcription task as completed and removes it from the list of active tasks. Use this to clean up resources after retrieving results. [See the documentation](https://docs.speech.palatine.ru/api-reference/transcribe/transcribe-polling-api/task-done)",
+  version: "0.0.1",
+  type: "action",
+  annotations: {
+    readOnlyHint: false,
+    destructiveHint: true,
+    openWorldHint: true,
+  },
+  props: {
+    app,
+    taskId: {
+      propDefinition: [
+        app,
+        "taskId",
+      ],
+    },
+  },
+  async run({ $ }) {
+    const {
+      app,
+      taskId,
+    } = this;
+
+    const response = await app.markTaskDone({
+      $,
+      taskId,
+    });
+
+    $.export("$summary", "Successfully marked task as done");
+    return response;
+  },
+};

package/actions/transcribe-audio/transcribe-audio.mjs

@@ -0,0 +1,133 @@
+import FormData from "form-data";
+import {
+  getFileStreamAndMetadata,
+  ConfigurationError,
+} from "@pipedream/platform";
+import app from "../../palatine_speech.app.mjs";
+
+export default {
+  key: "palatine_speech-transcribe-audio",
+  name: "Transcribe Audio",
+  description: "Starts an asynchronous transcription job for an audio or video file. Optionally wait for completion by enabling the 'Wait for Completion' option. [See the documentation](https://docs.speech.palatine.ru/api-reference/transcribe/transcribe-polling-api/transcribe)",
+  version: "0.0.1",
+  type: "action",
+  annotations: {
+    readOnlyHint: false,
+    destructiveHint: false,
+    openWorldHint: true,
+  },
+  props: {
+    app,
+    filePath: {
+      type: "string",
+      label: "File Path or URL",
+      description: "Provide either a file URL or a path to a file in the `/tmp` directory (for example, `/tmp/myFile.mp3`)",
+    },
+    model: {
+      propDefinition: [
+        app,
+        "model",
+      ],
+    },
+    fastInference: {
+      propDefinition: [
+        app,
+        "fastInference",
+      ],
+    },
+    waitForCompletion: {
+      type: "boolean",
+      label: "Wait for Completion",
+      description: "If enabled, the action will poll the task status until the transcription is complete before returning the result",
+      optional: true,
+    },
+    pollingInterval: {
+      type: "integer",
+      label: "Polling Interval (seconds)",
+      description: "Time to wait between status checks when waiting for completion. Only used if **Wait for Completion** is enabled. Defaults to `3` seconds if not specified.",
+      optional: true,
+      min: 1,
+      max: 60,
+    },
+    maxPollingAttempts: {
+      type: "integer",
+      label: "Max Polling Attempts",
+      description: "Maximum number of times to check the status before timing out. Only used if **Wait for Completion** is enabled. Defaults to `3` attempts if not specified.",
+      optional: true,
+      min: 1,
+      max: 20,
+    },
+    syncDir: {
+      type: "dir",
+      accessMode: "read",
+      sync: true,
+    },
+  },
+  async run({ $ }) {
+    const {
+      app,
+      filePath,
+      model,
+      fastInference,
+      waitForCompletion,
+      pollingInterval = 3,
+      maxPollingAttempts = 3,
+    } = this;
+
+    const data = new FormData();
+
+    const {
+      stream,
+      metadata,
+    } = await getFileStreamAndMetadata(filePath);
+
+    data.append("file", stream, {
+      contentType: metadata.contentType,
+      knownLength: metadata.size,
+      filename: metadata.name,
+    });
+
+    const response = await app.transcribeAudio({
+      $,
+      headers: data.getHeaders(),
+      params: {
+        model,
+        fast_inference: fastInference,
+      },
+      data,
+    });
+
+    const taskId = response.task_id;
+
+    if (!waitForCompletion) {
+      $.export("$summary", "Successfully started transcription job");
+      return response;
+    }
+
+    // Poll for completion
+    let attempts = 0;
+    let taskStatus;
+
+    while (attempts < maxPollingAttempts) {
+      await new Promise((resolve) => setTimeout(resolve, pollingInterval * 1000));
+
+      taskStatus = await app.getTaskStatus({
+        $,
+        taskId,
+      });
+
+      if (taskStatus.status === "success") {
+        $.export("$summary", "Transcription completed successfully");
+        return taskStatus;
+      }
+
+      if (taskStatus.status === "error") {
+        throw new ConfigurationError(`Transcription failed: ${taskStatus.error || "Unknown error"}`);
+      }
+
+      attempts++;
+    }
+
+    throw new ConfigurationError(`Transcription timed out after ${maxPollingAttempts} attempts`);
+  },
+};

package/common/constants.mjs

@@ -0,0 +1,7 @@
+const VERSION_PATH = "/api/v1";
+const BASE_URL = "https://api.palatine.ru";
+
+export default {
+  BASE_URL,
+  VERSION_PATH,
+};

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@pipedream/palatine_speech",
-  "version": "0.0.1",
+  "version": "0.1.0",
   "description": "Pipedream Palatine Speech Components",
   "main": "palatine_speech.app.mjs",
   "keywords": [
@@ -11,5 +11,8 @@
   "author": "Pipedream <support@pipedream.com> (https://pipedream.com/)",
   "publishConfig": {
     "access": "public"
+  },
+  "dependencies": {
+    "@pipedream/platform": "^3.1.1"
   }
 }

package/palatine_speech.app.mjs

@@ -1,11 +1,110 @@
+import { axios } from "@pipedream/platform";
+import constants from "./common/constants.mjs";
+
 export default {
   type: "app",
   app: "palatine_speech",
-  propDefinitions: {},
+  propDefinitions: {
+    taskId: {
+      type: "string",
+      label: "Task ID",
+      description: "The unique identifier of the transcription task",
+    },
+    model: {
+      type: "string",
+      label: "Recognition Model",
+      description: "The speech recognition model to use",
+      options: [
+        {
+          label: "Palatine Large Highspeed",
+          value: "palatine_large_highspeed",
+        },
+        {
+          label: "Palatine Small",
+          value: "palatine_small",
+        },
+      ],
+      optional: true,
+    },
+    fastInference: {
+      type: "boolean",
+      label: "Fast Inference",
+      description: "Enable accelerated inference for faster processing",
+      optional: true,
+    },
+    fileFormat: {
+      type: "string",
+      label: "File Format",
+      description: "The format for the downloaded transcription file",
+      options: [
+        "srt",
+        "vtt",
+        "txt",
+        "csv",
+        "xlsx",
+      ],
+    },
+    responseFormat: {
+      type: "string",
+      label: "Response Format",
+      description: "Format for the task status response",
+      options: [
+        "srt",
+        "vtt",
+      ],
+      optional: true,
+    },
+  },
   methods: {
-    // this.$auth contains connected account data
-    authKeys() {
-      console.log(Object.keys(this.$auth));
+    getUrl(path) {
+      return `${constants.BASE_URL}${constants.VERSION_PATH}${path}`;
+    },
+    getHeaders(headers) {
+      return {
+        "Authorization": `Bearer ${this.$auth.api_key}`,
+        ...headers,
+      };
+    },
+    _makeRequest({
+      $ = this, path, headers, ...opts
+    }) {
+      return axios($, {
+        url: this.getUrl(path),
+        headers: this.getHeaders(headers),
+        ...opts,
+      });
+    },
+    transcribeAudio(args = {}) {
+      return this._makeRequest({
+        method: "POST",
+        path: "/transcribe/do_transcribe",
+        ...args,
+      });
+    },
+    getTaskStatus({
+      taskId, ...args
+    }) {
+      return this._makeRequest({
+        path: `/transcribe/task_status/${taskId}`,
+        ...args,
+      });
+    },
+    downloadTranscription({
+      taskId, ...args
+    }) {
+      return this._makeRequest({
+        path: `/transcribe/download_as_file/${taskId}`,
+        ...args,
+      });
+    },
+    markTaskDone({
+      taskId, ...args
+    }) {
+      return this._makeRequest({
+        method: "POST",
+        path: `/transcribe/task_done/${taskId}`,
+        ...args,
+      });
     },
   },
-};
+};