ima2-gen 2.0.5 → 2.0.13

package/node_modules/ai/docs/07-reference/01-ai-sdk-core/10-generate-image.mdx

@@ -0,0 +1,251 @@
+---
+title: generateImage
+description: API Reference for generateImage.
+---
+
+# `generateImage()`
+
+Generates images based on a given prompt using an image model.
+
+It is ideal for use cases where you need to generate images programmatically,
+such as creating visual content or generating images for data augmentation.
+
+```ts
+import { generateImage } from 'ai';
+
+const { images } = await generateImage({
+  model: openai.image('dall-e-3'),
+  prompt: 'A futuristic cityscape at sunset',
+  n: 3,
+  size: '1024x1024',
+});
+
+console.log(images);
+```
+
+## Import
+
+<Snippet text={`import { generateImage } from "ai"`} prompt={false} />
+
+## API Signature
+
+### Parameters
+
+<PropertiesTable
+  content={[
+    {
+      name: 'model',
+      type: 'ImageModelV3',
+      description: 'The image model to use.',
+    },
+    {
+      name: 'prompt',
+      type: 'string | GenerateImagePrompt',
+      description: 'The input prompt to generate the image from.',
+      properties: [
+        {
+          type: 'GenerateImagePrompt',
+          type: 'object',
+          description: 'A prompt object for image editing',
+          parameters: [
+            {
+              name: 'images',
+              type: 'Array<DataContent>',
+              description:
+                'an image item can be one of: base64-encoded string, a `Uint8Array`, an `ArrayBuffer`, or a `Buffer`.',
+            },
+            {
+              name: 'text',
+              type: 'string',
+              description: 'The text prompt.',
+            },
+            {
+              name: 'mask',
+              type: 'DataContent',
+              description:
+                'base64-encoded string, a `Uint8Array`, an `ArrayBuffer`, or a `Buffer`.',
+            },
+          ],
+        },
+      ],
+    },
+    {
+      name: 'n',
+      type: 'number',
+      isOptional: true,
+      description: 'Number of images to generate.',
+    },
+    {
+      name: 'size',
+      type: 'string',
+      isOptional: true,
+      description:
+        'Size of the images to generate. Format: `{width}x{height}`.',
+    },
+    {
+      name: 'aspectRatio',
+      type: 'string',
+      isOptional: true,
+      description:
+        'Aspect ratio of the images to generate. Format: `{width}:{height}`.',
+    },
+    {
+      name: 'seed',
+      type: 'number',
+      isOptional: true,
+      description: 'Seed for the image generation.',
+    },
+    {
+      name: 'providerOptions',
+      type: 'ProviderOptions',
+      isOptional: true,
+      description: 'Additional provider-specific options.',
+    },
+    {
+      name: 'maxImagesPerCall',
+      type: 'number',
+      isOptional: true,
+      description:
+        'Maximum number of images to generate per API call. When n exceeds this value, multiple API calls will be made.',
+    },
+    {
+      name: 'maxRetries',
+      type: 'number',
+      isOptional: true,
+      description: 'Maximum number of retries. Default: 2.',
+    },
+    {
+      name: 'abortSignal',
+      type: 'AbortSignal',
+      isOptional: true,
+      description: 'An optional abort signal to cancel the call.',
+    },
+    {
+      name: 'headers',
+      type: 'Record<string, string>',
+      isOptional: true,
+      description: 'Additional HTTP headers for the request.',
+    },
+  ]}
+/>
+
+### Returns
+
+<PropertiesTable
+  content={[
+    {
+      name: 'image',
+      type: 'GeneratedFile',
+      description: 'The first image that was generated.',
+      properties: [
+        {
+          type: 'GeneratedFile',
+          parameters: [
+            {
+              name: 'base64',
+              type: 'string',
+              description: 'Image as a base64 encoded string.',
+            },
+            {
+              name: 'uint8Array',
+              type: 'Uint8Array',
+              description: 'Image as a Uint8Array.',
+            },
+            {
+              name: 'mediaType',
+              type: 'string',
+              description: 'The IANA media type of the image.',
+            },
+          ],
+        },
+      ],
+    },
+    {
+      name: 'images',
+      type: 'Array<GeneratedFile>',
+      description: 'All images that were generated.',
+      properties: [
+        {
+          type: 'GeneratedFile',
+          parameters: [
+            {
+              name: 'base64',
+              type: 'string',
+              description: 'Image as a base64 encoded string.',
+            },
+            {
+              name: 'uint8Array',
+              type: 'Uint8Array',
+              description: 'Image as a Uint8Array.',
+            },
+            {
+              name: 'mediaType',
+              type: 'string',
+              description: 'The IANA media type of the image.',
+            },
+          ],
+        },
+      ],
+    },
+    {
+      name: 'warnings',
+      type: 'Warning[]',
+      description:
+        'Warnings from the model provider (e.g. unsupported settings).',
+    },
+    {
+      name: 'usage',
+      type: 'ImageModelUsage',
+      description: 'The usage statistics for the image generation.',
+      properties: [
+        {
+          type: 'ImageModelUsage',
+          parameters: [
+            {
+              name: 'imagesGenerated',
+              type: 'number',
+              description: 'The total number of images generated.',
+            },
+          ],
+        },
+      ],
+    },
+    {
+      name: 'providerMetadata',
+      type: 'ImageModelProviderMetadata',
+      isOptional: true,
+      description:
+        'Optional metadata from the provider. The outer key is the provider name. The inner values are the metadata. An `images` key is always present in the metadata and is an array with the same length as the top level `images` key. Details depend on the provider.',
+    },
+    {
+      name: 'responses',
+      type: 'Array<ImageModelResponseMetadata>',
+      description:
+        'Response metadata from the provider. There may be multiple responses if we made multiple calls to the model.',
+      properties: [
+        {
+          type: 'ImageModelResponseMetadata',
+          parameters: [
+            {
+              name: 'timestamp',
+              type: 'Date',
+              description: 'Timestamp for the start of the generated response.',
+            },
+            {
+              name: 'modelId',
+              type: 'string',
+              description:
+                'The ID of the response model that was used to generate the response.',
+            },
+            {
+              name: 'headers',
+              type: 'Record<string, string>',
+              isOptional: true,
+              description: 'Response headers.',
+            },
+          ],
+        },
+      ],
+    },
+  ]}
+/>

package/node_modules/ai/docs/07-reference/01-ai-sdk-core/11-transcribe.mdx

@@ -0,0 +1,152 @@
+---
+title: transcribe
+description: API Reference for transcribe.
+---
+
+# `transcribe()`
+
+<Note type="warning">`transcribe` is an experimental feature.</Note>
+
+Generates a transcript from an audio file.
+
+```ts
+import { experimental_transcribe as transcribe } from 'ai';
+import { openai } from '@ai-sdk/openai';
+import { readFile } from 'fs/promises';
+
+const { text: transcript } = await transcribe({
+  model: openai.transcription('whisper-1'),
+  audio: await readFile('audio.mp3'),
+});
+
+console.log(transcript);
+```
+
+## Import
+
+<Snippet
+  text={`import { experimental_transcribe as transcribe } from "ai"`}
+  prompt={false}
+/>
+
+## API Signature
+
+### Parameters
+
+<PropertiesTable
+  content={[
+    {
+      name: 'model',
+      type: 'TranscriptionModelV3',
+      description: 'The transcription model to use.',
+    },
+    {
+      name: 'audio',
+      type: 'DataContent (string | Uint8Array | ArrayBuffer | Buffer) | URL',
+      description: 'The audio file to generate the transcript from.',
+    },
+    {
+      name: 'providerOptions',
+      type: 'Record<string, JSONObject>',
+      isOptional: true,
+      description: 'Additional provider-specific options.',
+    },
+    {
+      name: 'maxRetries',
+      type: 'number',
+      isOptional: true,
+      description: 'Maximum number of retries. Default: 2.',
+    },
+    {
+      name: 'abortSignal',
+      type: 'AbortSignal',
+      isOptional: true,
+      description: 'An optional abort signal to cancel the call.',
+    },
+    {
+      name: 'headers',
+      type: 'Record<string, string>',
+      isOptional: true,
+      description: 'Additional HTTP headers for the request.',
+    },
+    {
+      name: 'download',
+      type: '(options: { url: URL; abortSignal?: AbortSignal }) => Promise<{ data: Uint8Array; mediaType: string | undefined }>',
+      isOptional: true,
+      description:
+        'Custom download function for fetching audio from URLs. Use `createDownload()` from `ai` to create a download function with custom size limits, e.g. `createDownload({ maxBytes: 50 * 1024 * 1024 })`. Default: built-in download with 2 GiB limit.',
+    },
+  ]}
+/>
+
+### Returns
+
+<PropertiesTable
+  content={[
+    {
+      name: 'text',
+      type: 'string',
+      description: 'The complete transcribed text from the audio input.',
+    },
+    {
+      name: 'segments',
+      type: 'Array<{ text: string; startSecond: number; endSecond: number }>',
+      description:
+        'An array of transcript segments, each containing a portion of the transcribed text along with its start and end times in seconds.',
+    },
+    {
+      name: 'language',
+      type: 'string | undefined',
+      description:
+        'The language of the transcript in ISO-639-1 format e.g. "en" for English.',
+    },
+    {
+      name: 'durationInSeconds',
+      type: 'number | undefined',
+      description: 'The duration of the transcript in seconds.',
+    },
+    {
+      name: 'warnings',
+      type: 'Warning[]',
+      description:
+        'Warnings from the model provider (e.g. unsupported settings).',
+    },
+    {
+      name: 'providerMetadata',
+      type: 'Record<string, JSONObject>',
+      isOptional: true,
+      description:
+        'Optional metadata from the provider. The outer key is the provider name. The inner values are the metadata. Details depend on the provider.',
+    },
+    {
+      name: 'responses',
+      type: 'Array<TranscriptionModelResponseMetadata>',
+      description:
+        'Response metadata from the provider. There may be multiple responses if we made multiple calls to the model.',
+      properties: [
+        {
+          type: 'TranscriptionModelResponseMetadata',
+          parameters: [
+            {
+              name: 'timestamp',
+              type: 'Date',
+              description: 'Timestamp for the start of the generated response.',
+            },
+            {
+              name: 'modelId',
+              type: 'string',
+              description:
+                'The ID of the response model that was used to generate the response.',
+            },
+            {
+              name: 'headers',
+              type: 'Record<string, string>',
+              isOptional: true,
+              description: 'Response headers.',
+            },
+          ],
+        },
+      ],
+    },
+  ]}
+/>

package/node_modules/ai/docs/07-reference/01-ai-sdk-core/12-generate-speech.mdx

@@ -0,0 +1,221 @@
+---
+title: generateSpeech
+description: API Reference for generateSpeech.
+---
+
+# `generateSpeech()`
+
+<Note type="warning">`generateSpeech` is an experimental feature.</Note>
+
+Generates speech audio from text.
+
+```ts
+import { experimental_generateSpeech as generateSpeech } from 'ai';
+import { openai } from '@ai-sdk/openai';
+
+const { audio } = await generateSpeech({
+  model: openai.speech('tts-1'),
+  text: 'Hello from the AI SDK!',
+  voice: 'alloy',
+});
+
+console.log(audio);
+```
+
+## Examples
+
+### OpenAI
+
+```ts
+import { experimental_generateSpeech as generateSpeech } from 'ai';
+import { openai } from '@ai-sdk/openai';
+
+const { audio } = await generateSpeech({
+  model: openai.speech('tts-1'),
+  text: 'Hello from the AI SDK!',
+  voice: 'alloy',
+});
+```
+
+### ElevenLabs
+
+```ts
+import { experimental_generateSpeech as generateSpeech } from 'ai';
+import { elevenlabs } from '@ai-sdk/elevenlabs';
+
+const { audio } = await generateSpeech({
+  model: elevenlabs.speech('eleven_multilingual_v2'),
+  text: 'Hello from the AI SDK!',
+  voice: 'your-voice-id', // Required: get this from your ElevenLabs account
+});
+```
+
+## Import
+
+<Snippet
+  text={`import { experimental_generateSpeech as generateSpeech } from "ai"`}
+  prompt={false}
+/>
+
+## API Signature
+
+### Parameters
+
+<PropertiesTable
+  content={[
+    {
+      name: 'model',
+      type: 'SpeechModelV3',
+      description: 'The speech model to use.',
+    },
+    {
+      name: 'text',
+      type: 'string',
+      description: 'The text to generate the speech from.',
+    },
+    {
+      name: 'voice',
+      type: 'string',
+      isOptional: true,
+      description: 'The voice to use for the speech.',
+    },
+    {
+      name: 'outputFormat',
+      type: 'string',
+      isOptional: true,
+      description:
+        'The output format to use for the speech e.g. "mp3", "wav", etc.',
+    },
+    {
+      name: 'instructions',
+      type: 'string',
+      isOptional: true,
+      description: 'Instructions for the speech generation.',
+    },
+    {
+      name: 'speed',
+      type: 'number',
+      isOptional: true,
+      description: 'The speed of the speech generation.',
+    },
+    {
+      name: 'language',
+      type: 'string',
+      isOptional: true,
+      description:
+        'The language for speech generation. This should be an ISO 639-1 language code (e.g. "en", "es", "fr") or "auto" for automatic language detection. Provider support varies.',
+    },
+    {
+      name: 'providerOptions',
+      type: 'Record<string, JSONObject>',
+      isOptional: true,
+      description: 'Additional provider-specific options.',
+    },
+    {
+      name: 'maxRetries',
+      type: 'number',
+      isOptional: true,
+      description: 'Maximum number of retries. Default: 2.',
+    },
+    {
+      name: 'abortSignal',
+      type: 'AbortSignal',
+      isOptional: true,
+      description: 'An optional abort signal to cancel the call.',
+    },
+    {
+      name: 'headers',
+      type: 'Record<string, string>',
+      isOptional: true,
+      description: 'Additional HTTP headers for the request.',
+    },
+  ]}
+/>
+
+### Returns
+
+<PropertiesTable
+  content={[
+    {
+      name: 'audio',
+      type: 'GeneratedAudioFile',
+      description: 'The generated audio.',
+      properties: [
+        {
+          type: 'GeneratedAudioFile',
+          parameters: [
+            {
+              name: 'base64',
+              type: 'string',
+              description: 'Audio as a base64 encoded string.',
+            },
+            {
+              name: 'uint8Array',
+              type: 'Uint8Array',
+              description: 'Audio as a Uint8Array.',
+            },
+            {
+              name: 'mediaType',
+              type: 'string',
+              description: 'Media type of the audio (e.g. "audio/mpeg").',
+            },
+            {
+              name: 'format',
+              type: 'string',
+              description: 'Format of the audio (e.g. "mp3").',
+            },
+          ],
+        },
+      ],
+    },
+    {
+      name: 'warnings',
+      type: 'Warning[]',
+      description:
+        'Warnings from the model provider (e.g. unsupported settings).',
+    },
+    {
+      name: 'providerMetadata',
+      type: 'Record<string, JSONObject>',
+      isOptional: true,
+      description:
+        'Optional metadata from the provider. The outer key is the provider name. The inner values are the metadata. Details depend on the provider.',
+    },
+    {
+      name: 'responses',
+      type: 'Array<SpeechModelResponseMetadata>',
+      description:
+        'Response metadata from the provider. There may be multiple responses if we made multiple calls to the model.',
+      properties: [
+        {
+          type: 'SpeechModelResponseMetadata',
+          parameters: [
+            {
+              name: 'timestamp',
+              type: 'Date',
+              description: 'Timestamp for the start of the generated response.',
+            },
+            {
+              name: 'modelId',
+              type: 'string',
+              description:
+                'The ID of the response model that was used to generate the response.',
+            },
+            {
+              name: 'body',
+              isOptional: true,
+              type: 'unknown',
+              description: 'Optional response body.',
+            },
+            {
+              name: 'headers',
+              type: 'Record<string, string>',
+              isOptional: true,
+              description: 'Response headers.',
+            },
+          ],
+        },
+      ],
+    },
+  ]}
+/>