@speechall/sdk 0.0.1

package/dist/esm/configuration.js

@@ -0,0 +1,21 @@
+export class Configuration {
+    constructor(param = {}) {
+        this.apiKey = param.apiKey;
+        this.username = param.username;
+        this.password = param.password;
+        this.accessToken = param.accessToken;
+        this.basePath = param.basePath;
+        this.serverIndex = param.serverIndex;
+        this.baseOptions = {
+            ...param.baseOptions,
+            headers: {
+                ...param.baseOptions?.headers,
+            },
+        };
+        this.formDataCtor = param.formDataCtor;
+    }
+    isJsonMime(mime) {
+        const jsonMime = new RegExp('^(application\/json|[^;/ \t]+\/[^;/ \t]+[+]json)[ \t]*(;.*)?$', 'i');
+        return mime !== null && (jsonMime.test(mime) || mime.toLowerCase() === 'application/json-patch+json');
+    }
+}

package/dist/esm/example.js

@@ -0,0 +1,131 @@
+import { Configuration, SpeechToTextApi, ReplacementRulesApi, TranscriptionModelIdentifier } from './index.js';
+async function main() {
+    const config = new Configuration({
+        apiKey: process.env.SPEECHALL_API_KEY || 'your-api-key-here',
+        basePath: 'https://api.speechall.com'
+    });
+    const speechApi = new SpeechToTextApi(config);
+    const rulesApi = new ReplacementRulesApi(config);
+    try {
+        console.log('Fetching available models...');
+        const models = await speechApi.listSpeechToTextModels();
+        console.log('Available models:');
+        models.data.slice(0, 3).forEach(model => {
+            console.log(`  - ${model.id}: ${model.display_name} (${model.provider})`);
+            console.log(`    Languages: ${model.supported_languages?.join(', ')}`);
+            console.log(`    Cost: $${model.cost_per_second_usd}/second\n`);
+        });
+        console.log('Example 1: Basic transcription...');
+        const basicOptions = {
+            file_url: 'https://example.com/sample-audio.mp3',
+            model: TranscriptionModelIdentifier.DeepgramNova2General,
+            language: 'en',
+            output_format: 'json'
+        };
+        const basicResult = await speechApi.transcribeRemote(basicOptions);
+        console.log('Basic transcription:', basicResult.data.text);
+        console.log('\nExample 2: Advanced transcription...');
+        const advancedOptions = {
+            file_url: 'https://example.com/meeting-audio.mp3',
+            model: TranscriptionModelIdentifier.DeepgramNova2Meeting,
+            language: 'en',
+            output_format: 'json',
+            diarization: true,
+            punctuation: true,
+            timestamp_granularity: 'word',
+            speakers_expected: 3,
+            custom_vocabulary: ['API', 'TypeScript', 'Speechall']
+        };
+        const advancedResult = await speechApi.transcribeRemote(advancedOptions);
+        console.log('Advanced transcription:', advancedResult.data.text);
+        console.log('\nExample 3: Creating replacement rules...');
+        const rulesetResponse = await rulesApi.createReplacementRuleset({
+            name: 'Technical Terms Enhancement',
+            rules: [
+                {
+                    kind: 'exact',
+                    search: 'API',
+                    replacement: 'A.P.I.',
+                    caseSensitive: false
+                },
+                {
+                    kind: 'regex',
+                    pattern: '\\b(\\d+)\\s*dollars?\\b',
+                    replacement: '$$$1',
+                    flags: ['i']
+                }
+            ]
+        });
+        console.log('Created ruleset with ID:', rulesetResponse.data.id);
+        console.log('\nExample 4: OpenAI-compatible transcription...');
+        console.log('OpenAI-compatible endpoint would be used here with file upload');
+        console.log('\nExample 5: Direct file upload transcription...');
+        try {
+            const audioData = new Uint8Array(1024);
+            const audioFile = new File([audioData], 'sample-audio.wav', {
+                type: 'audio/wav'
+            });
+            console.log('Transcribing uploaded file:', audioFile.name);
+            const fileResult = await speechApi.transcribe(TranscriptionModelIdentifier.DeepgramNova2General, audioFile, 'en', 'json', undefined, true, 'word', false, 'Please transcribe this audio file clearly', 0.1);
+            console.log('Direct file transcription result:', fileResult.data);
+        }
+        catch (error) {
+            console.log('File transcription example (simulated file):', error.message);
+            console.log('In a real implementation, you would provide actual audio file data');
+        }
+        console.log('\n--- Browser File Input Example ---');
+        console.log(`
+// HTML:
+// <input type="file" id="audioFile" accept="audio/*" />
+// <button onclick="transcribeFile()">Transcribe</button>
+
+async function transcribeFile() {
+  const fileInput = document.getElementById('audioFile') as HTMLInputElement;
+  const file = fileInput.files?.[0];
+  
+  if (!file) {
+    alert('Please select an audio file');
+    return;
+  }
+
+  try {
+    const result = await speechApi.transcribe(
+      TranscriptionModelIdentifier.DeepgramNova2General,
+      file,
+      'en',
+      'json',
+      undefined, // no ruleset
+      true,      // punctuation
+      'segment', // timestamp granularity
+      true,      // diarization
+      'Transcribe this uploaded audio file' // prompt
+    );
+    
+    console.log('Transcription:', result.data.text);
+    
+    // Handle detailed response if format is 'json'
+    if ('segments' in result.data) {
+      result.data.segments?.forEach((segment, index) => {
+        console.log(\`Segment \${index + 1}: \${segment.text}\`);
+        if (segment.speaker) {
+          console.log(\`  Speaker: \${segment.speaker}\`);
+        }
+        if (segment.start && segment.end) {
+          console.log(\`  Time: \${segment.start}s - \${segment.end}s\`);
+        }
+      });
+    }
+  } catch (error) {
+    console.error('Transcription failed:', error);
+  }
+}
+    `);
+    }
+    catch (error) {
+        console.error('Error occurred:', error.response?.data || error.message);
+    }
+}
+if (require.main === module) {
+    main().catch(console.error);
+}
+export { main as example };

package/dist/esm/index.js

@@ -0,0 +1,2 @@
+export * from "./api.js";
+export * from "./configuration.js";

package/dist/example.d.ts

@@ -0,0 +1,3 @@
+declare function main(): Promise<void>;
+export { main as example };
+//# sourceMappingURL=example.d.ts.map

package/dist/example.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"example.d.ts","sourceRoot":"","sources":["../example.ts"],"names":[],"mappings":"AAUA,iBAAe,IAAI,IAAI,OAAO,CAAC,IAAI,CAAC,CAiLnC;AAOD,OAAO,EAAE,IAAI,IAAI,OAAO,EAAE,CAAC"}

package/dist/example.js

@@ -0,0 +1,133 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.example = main;
+const index_1 = require("./index");
+async function main() {
+    const config = new index_1.Configuration({
+        apiKey: process.env.SPEECHALL_API_KEY || 'your-api-key-here',
+        basePath: 'https://api.speechall.com'
+    });
+    const speechApi = new index_1.SpeechToTextApi(config);
+    const rulesApi = new index_1.ReplacementRulesApi(config);
+    try {
+        console.log('Fetching available models...');
+        const models = await speechApi.listSpeechToTextModels();
+        console.log('Available models:');
+        models.data.slice(0, 3).forEach(model => {
+            console.log(`  - ${model.id}: ${model.display_name} (${model.provider})`);
+            console.log(`    Languages: ${model.supported_languages?.join(', ')}`);
+            console.log(`    Cost: $${model.cost_per_second_usd}/second\n`);
+        });
+        console.log('Example 1: Basic transcription...');
+        const basicOptions = {
+            file_url: 'https://example.com/sample-audio.mp3',
+            model: index_1.TranscriptionModelIdentifier.DeepgramNova2General,
+            language: 'en',
+            output_format: 'json'
+        };
+        const basicResult = await speechApi.transcribeRemote(basicOptions);
+        console.log('Basic transcription:', basicResult.data.text);
+        console.log('\nExample 2: Advanced transcription...');
+        const advancedOptions = {
+            file_url: 'https://example.com/meeting-audio.mp3',
+            model: index_1.TranscriptionModelIdentifier.DeepgramNova2Meeting,
+            language: 'en',
+            output_format: 'json',
+            diarization: true,
+            punctuation: true,
+            timestamp_granularity: 'word',
+            speakers_expected: 3,
+            custom_vocabulary: ['API', 'TypeScript', 'Speechall']
+        };
+        const advancedResult = await speechApi.transcribeRemote(advancedOptions);
+        console.log('Advanced transcription:', advancedResult.data.text);
+        console.log('\nExample 3: Creating replacement rules...');
+        const rulesetResponse = await rulesApi.createReplacementRuleset({
+            name: 'Technical Terms Enhancement',
+            rules: [
+                {
+                    kind: 'exact',
+                    search: 'API',
+                    replacement: 'A.P.I.',
+                    caseSensitive: false
+                },
+                {
+                    kind: 'regex',
+                    pattern: '\\b(\\d+)\\s*dollars?\\b',
+                    replacement: '$$$1',
+                    flags: ['i']
+                }
+            ]
+        });
+        console.log('Created ruleset with ID:', rulesetResponse.data.id);
+        console.log('\nExample 4: OpenAI-compatible transcription...');
+        console.log('OpenAI-compatible endpoint would be used here with file upload');
+        console.log('\nExample 5: Direct file upload transcription...');
+        try {
+            const audioData = new Uint8Array(1024);
+            const audioFile = new File([audioData], 'sample-audio.wav', {
+                type: 'audio/wav'
+            });
+            console.log('Transcribing uploaded file:', audioFile.name);
+            const fileResult = await speechApi.transcribe(index_1.TranscriptionModelIdentifier.DeepgramNova2General, audioFile, 'en', 'json', undefined, true, 'word', false, 'Please transcribe this audio file clearly', 0.1);
+            console.log('Direct file transcription result:', fileResult.data);
+        }
+        catch (error) {
+            console.log('File transcription example (simulated file):', error.message);
+            console.log('In a real implementation, you would provide actual audio file data');
+        }
+        console.log('\n--- Browser File Input Example ---');
+        console.log(`
+// HTML:
+// <input type="file" id="audioFile" accept="audio/*" />
+// <button onclick="transcribeFile()">Transcribe</button>
+
+async function transcribeFile() {
+  const fileInput = document.getElementById('audioFile') as HTMLInputElement;
+  const file = fileInput.files?.[0];
+  
+  if (!file) {
+    alert('Please select an audio file');
+    return;
+  }
+
+  try {
+    const result = await speechApi.transcribe(
+      TranscriptionModelIdentifier.DeepgramNova2General,
+      file,
+      'en',
+      'json',
+      undefined, // no ruleset
+      true,      // punctuation
+      'segment', // timestamp granularity
+      true,      // diarization
+      'Transcribe this uploaded audio file' // prompt
+    );
+    
+    console.log('Transcription:', result.data.text);
+    
+    // Handle detailed response if format is 'json'
+    if ('segments' in result.data) {
+      result.data.segments?.forEach((segment, index) => {
+        console.log(\`Segment \${index + 1}: \${segment.text}\`);
+        if (segment.speaker) {
+          console.log(\`  Speaker: \${segment.speaker}\`);
+        }
+        if (segment.start && segment.end) {
+          console.log(\`  Time: \${segment.start}s - \${segment.end}s\`);
+        }
+      });
+    }
+  } catch (error) {
+    console.error('Transcription failed:', error);
+  }
+}
+    `);
+    }
+    catch (error) {
+        console.error('Error occurred:', error.response?.data || error.message);
+    }
+}
+if (require.main === module) {
+    main().catch(console.error);
+}

package/dist/index.d.ts

@@ -0,0 +1,3 @@
+export * from "./api";
+export * from "./configuration";
+//# sourceMappingURL=index.d.ts.map

package/dist/index.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../index.ts"],"names":[],"mappings":"AAeA,cAAc,OAAO,CAAC;AACtB,cAAc,iBAAiB,CAAC"}

package/dist/index.js

@@ -0,0 +1,18 @@
+"use strict";
+var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    var desc = Object.getOwnPropertyDescriptor(m, k);
+    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
+      desc = { enumerable: true, get: function() { return m[k]; } };
+    }
+    Object.defineProperty(o, k2, desc);
+}) : (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    o[k2] = m[k];
+}));
+var __exportStar = (this && this.__exportStar) || function(m, exports) {
+    for (var p in m) if (p !== "default" && !Object.prototype.hasOwnProperty.call(exports, p)) __createBinding(exports, m, p);
+};
+Object.defineProperty(exports, "__esModule", { value: true });
+__exportStar(require("./api"), exports);
+__exportStar(require("./configuration"), exports);

package/package.json

@@ -0,0 +1,62 @@
+{
+  "name": "@speechall/sdk",
+  "version": "0.0.1",
+  "description": "TypeScript SDK for the Speechall API - A powerful and flexible speech-to-text service",
+  "main": "dist/index.js",
+  "types": "dist/index.d.ts",
+  "module": "dist/esm/index.js",
+  "sideEffects": false,
+  "files": [
+    "dist/**/*",
+    "README.md",
+    "LICENSE"
+  ],
+  "scripts": {
+    "build": "npm run build:cjs && npm run build:esm",
+    "build:cjs": "tsc -p tsconfig.json",
+    "build:esm": "tsc -p tsconfig.esm.json && node scripts/fix-esm-imports.js",
+    "clean": "rimraf dist",
+    "prepublishOnly": "npm run clean && npm run build",
+    "test": "echo \"Error: no test specified\" && exit 1",
+    "lint": "eslint . --ext .ts",
+    "lint:fix": "eslint . --ext .ts --fix"
+  },
+  "keywords": [
+    "speechall",
+    "speech-to-text",
+    "stt",
+    "transcription",
+    "audio",
+    "voice",
+    "api",
+    "typescript",
+    "sdk"
+  ],
+  "author": "Speechall",
+  "license": "MIT",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/speechall/speechall-typescript-sdk.git"
+  },
+  "bugs": {
+    "url": "https://github.com/speechall/speechall-typescript-sdk/issues"
+  },
+  "homepage": "https://github.com/speechall/speechall-typescript-sdk#readme",
+  "dependencies": {
+    "axios": "^1.6.0"
+  },
+  "devDependencies": {
+    "@semantic-release/changelog": "^6.0.3",
+    "@semantic-release/git": "^10.0.1",
+    "@types/node": "^20.0.0",
+    "@typescript-eslint/eslint-plugin": "^6.0.0",
+    "@typescript-eslint/parser": "^6.0.0",
+    "eslint": "^8.0.0",
+    "rimraf": "^5.0.0",
+    "semantic-release": "^22.0.12",
+    "typescript": "^5.0.0"
+  },
+  "engines": {
+    "node": ">=16"
+  }
+}