@juspay/neurolink 8.7.0 → 8.8.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CHANGELOG.md CHANGED
@@ -1,3 +1,9 @@
1
+ ## [8.8.0](https://github.com/juspay/neurolink/compare/v8.7.0...v8.8.0) (2025-12-11)
2
+
3
+ ### Features
4
+
5
+ - **(types):** add AudioProviderConfig type definition for transcription providers ([c34f437](https://github.com/juspay/neurolink/commit/c34f437455fba20b803b84811b9dda143351427e))
6
+
1
7
  ## [8.7.0](https://github.com/juspay/neurolink/compare/v8.6.0...v8.7.0) (2025-12-10)
2
8
 
3
9
  ### Features
@@ -80,6 +80,52 @@ export type PDFProcessorOptions = {
80
80
  maxSizeMB?: number;
81
81
  bedrockApiMode?: "converse" | "invokeModel";
82
82
  };
83
+ /**
84
+ * Audio provider configuration for transcription services
85
+ *
86
+ * Describes the capabilities and limitations of each audio transcription provider
87
+ * (e.g., OpenAI Whisper, Google Speech-to-Text, Azure Speech Services).
88
+ *
89
+ * @example OpenAI Whisper configuration
90
+ * ```typescript
91
+ * const openaiConfig: AudioProviderConfig = {
92
+ * maxSizeMB: 25,
93
+ * maxDurationSeconds: 600,
94
+ * supportedFormats: ['mp3', 'mp4', 'm4a', 'wav', 'webm'],
95
+ * supportsLanguageDetection: true,
96
+ * requiresApiKey: true,
97
+ * costPer60s: 0.006 // $0.006 per minute
98
+ * };
99
+ * ```
100
+ *
101
+ * @example Google Speech-to-Text configuration
102
+ * ```typescript
103
+ * const googleConfig: AudioProviderConfig = {
104
+ * maxSizeMB: 10,
105
+ * maxDurationSeconds: 480,
106
+ * supportedFormats: ['flac', 'wav', 'mp3', 'ogg'],
107
+ * supportsLanguageDetection: true,
108
+ * requiresApiKey: true,
109
+ * costPer15s: 0.004 // $0.016 per minute ($0.004 per 15 seconds)
110
+ * };
111
+ * ```
112
+ */
113
+ export type AudioProviderConfig = {
114
+ /** Maximum audio file size in megabytes */
115
+ maxSizeMB: number;
116
+ /** Maximum audio duration in seconds */
117
+ maxDurationSeconds: number;
118
+ /** Supported audio formats (e.g., 'mp3', 'wav', 'm4a', 'flac', 'ogg') */
119
+ supportedFormats: string[];
120
+ /** Whether the provider supports automatic language detection */
121
+ supportsLanguageDetection: boolean;
122
+ /** Whether the provider requires an API key for authentication */
123
+ requiresApiKey: boolean;
124
+ /** Optional: Cost per 60 seconds of audio in USD */
125
+ costPer60s?: number;
126
+ /** Optional: Cost per 15 seconds of audio in USD */
127
+ costPer15s?: number;
128
+ };
83
129
  /**
84
130
  * Audio processor options
85
131
  */
@@ -80,6 +80,52 @@ export type PDFProcessorOptions = {
80
80
  maxSizeMB?: number;
81
81
  bedrockApiMode?: "converse" | "invokeModel";
82
82
  };
83
+ /**
84
+ * Audio provider configuration for transcription services
85
+ *
86
+ * Describes the capabilities and limitations of each audio transcription provider
87
+ * (e.g., OpenAI Whisper, Google Speech-to-Text, Azure Speech Services).
88
+ *
89
+ * @example OpenAI Whisper configuration
90
+ * ```typescript
91
+ * const openaiConfig: AudioProviderConfig = {
92
+ * maxSizeMB: 25,
93
+ * maxDurationSeconds: 600,
94
+ * supportedFormats: ['mp3', 'mp4', 'm4a', 'wav', 'webm'],
95
+ * supportsLanguageDetection: true,
96
+ * requiresApiKey: true,
97
+ * costPer60s: 0.006 // $0.006 per minute
98
+ * };
99
+ * ```
100
+ *
101
+ * @example Google Speech-to-Text configuration
102
+ * ```typescript
103
+ * const googleConfig: AudioProviderConfig = {
104
+ * maxSizeMB: 10,
105
+ * maxDurationSeconds: 480,
106
+ * supportedFormats: ['flac', 'wav', 'mp3', 'ogg'],
107
+ * supportsLanguageDetection: true,
108
+ * requiresApiKey: true,
109
+ * costPer15s: 0.004 // $0.016 per minute ($0.004 per 15 seconds)
110
+ * };
111
+ * ```
112
+ */
113
+ export type AudioProviderConfig = {
114
+ /** Maximum audio file size in megabytes */
115
+ maxSizeMB: number;
116
+ /** Maximum audio duration in seconds */
117
+ maxDurationSeconds: number;
118
+ /** Supported audio formats (e.g., 'mp3', 'wav', 'm4a', 'flac', 'ogg') */
119
+ supportedFormats: string[];
120
+ /** Whether the provider supports automatic language detection */
121
+ supportsLanguageDetection: boolean;
122
+ /** Whether the provider requires an API key for authentication */
123
+ requiresApiKey: boolean;
124
+ /** Optional: Cost per 60 seconds of audio in USD */
125
+ costPer60s?: number;
126
+ /** Optional: Cost per 15 seconds of audio in USD */
127
+ costPer15s?: number;
128
+ };
83
129
  /**
84
130
  * Audio processor options
85
131
  */
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@juspay/neurolink",
3
- "version": "8.7.0",
3
+ "version": "8.8.0",
4
4
  "description": "Universal AI Development Platform with working MCP integration, multi-provider support, and professional CLI. Built-in tools operational, 58+ external MCP servers discoverable. Connect to filesystem, GitHub, database operations, and more. Build, test, and deploy AI applications with 9 major providers: OpenAI, Anthropic, Google AI, AWS Bedrock, Azure, Hugging Face, Ollama, and Mistral AI.",
5
5
  "author": {
6
6
  "name": "Juspay Technologies",