@runpod/ai-sdk-provider 0.11.1 → 1.0.0

package/CHANGELOG.md

@@ -1,5 +1,47 @@
 # @runpod/ai-sdk-provider
 
+## 1.0.0
+
+### Major Changes
+
+- 7fa7435: Release 1.0.0 - AI SDK v6 Compatibility
+
+  This release marks the first stable version of the Runpod AI SDK Provider, coinciding with the AI SDK v6 release.
+
+  ### Breaking Changes
+  - Now requires AI SDK v6 (`ai@6.x`) - users on AI SDK v5 must upgrade
+  - Updated to V3 provider interfaces (`LanguageModelV3`, `ImageModelV3`, `SpeechModelV3`)
+
+  ### New Features
+  - **Standardized `files` parameter support**: Image models now accept the AI SDK standard `files` parameter for image editing, supporting both URLs and base64 data
+  - Legacy `providerOptions.runpod.images` still works but `files` is now the recommended approach
+
+  ### Dependencies
+  - `@ai-sdk/provider`: ^2.0.0 → ^3.0.0
+  - `@ai-sdk/provider-utils`: ^3.0.5 → ^4.0.0
+  - `@ai-sdk/openai-compatible`: ^1.0.11 → ^2.0.0
+
+  ### What's Unchanged
+  - Public API remains identical - no code changes required for users already on AI SDK v6
+  - All language models, image models, and speech models work the same way
+
+### Patch Changes
+
+- 7fa7435: docs: expand speech docs for chatterbox turbo
+
+## 0.12.0
+
+### Minor Changes
+
+- dcc2cc5: Add support for speech generation with `resembleai/chatterbox-turbo` model:
+  - `speechModel()` and `speech()` methods for text-to-speech
+  - Voice cloning via URL (5-10 seconds of audio)
+  - 20 built-in voices
+
+### Patch Changes
+
+- ace58c2: Add comprehensive documentation for Pruna and Nano Banana Pro models, including all supported aspect ratios, resolutions, and output formats. Update examples to use standard AI SDK options where possible.
+
 ## 0.11.1
 
 ### Patch Changes

package/README.md

@@ -1,5 +1,7 @@
 # Runpod AI SDK Provider
 
+![Runpod AI SDK Provider banner](https://image.runpod.ai/runpod/ai-sdk-provider/banner.jpg)
+
 The **Runpod provider** for the [AI SDK](https://ai-sdk.dev/docs) contains language model and image generation support for [Runpod's](https://runpod.io) public endpoints.
 
 ## Setup
@@ -104,7 +106,11 @@ for await (const delta of textStream) {
 }
 ```
 
-### Model Capabilities
+### Examples
+
+Check out our [examples](https://github.com/runpod/examples/tree/main/ai-sdk/getting-started) for more code snippets on how to use all the different models.
+
+### Supported Models
 
 | Model ID                          | Description                                                         | Streaming | Object Generation | Tool Usage | Reasoning Notes           |
 | --------------------------------- | ------------------------------------------------------------------- | --------- | ----------------- | ---------- | ------------------------- |
@@ -196,23 +202,27 @@ console.log(result.success ? result.data : parsed);
 
 ## Image Models
 
-You can create Runpod image models using the `.imageModel()` factory method.
+With image models you can:
 
-### Basic Usage
+- **Text-to-image**: generate a new image from a text prompt.
+- **Edit image**: transform an existing image by providing reference image(s).
+
+All examples use the AI SDK's `experimental_generateImage` and `runpod.image(modelId)`.
+
+### Text-to-Image
 
 ```ts
 import { runpod } from '@runpod/ai-sdk-provider';
 import { experimental_generateImage as generateImage } from 'ai';
+import { writeFileSync } from 'fs';
 
 const { image } = await generateImage({
-  model: runpod.imageModel('qwen/qwen-image'),
+  model: runpod.image('pruna/p-image-t2i'),
   prompt: 'A serene mountain landscape at sunset',
   aspectRatio: '4:3',
 });
 
-// Save to filesystem
-import { writeFileSync } from 'fs';
-writeFileSync('landscape.jpg', image.uint8Array);
+writeFileSync('image.png', image.uint8Array);
 ```
 
 **Returns:**
@@ -222,154 +232,277 @@ writeFileSync('landscape.jpg', image.uint8Array);
 - `image.mediaType` - MIME type ('image/jpeg' or 'image/png')
 - `warnings` - Array of any warnings about unsupported parameters
 
-### Model Capabilities
-
-| Model ID                               | Description                     | Supported Aspect Ratios               |
-| -------------------------------------- | ------------------------------- | ------------------------------------- |
-| `bytedance/seedream-3.0`               | Advanced text-to-image model    | 1:1, 4:3, 3:4                         |
-| `bytedance/seedream-4.0`               | Text-to-image (v4)              | 1:1 (supports 1024, 2048, 4096)       |
-| `bytedance/seedream-4.0-edit`          | Image editing (v4, multi-image) | 1:1 (supports 1024, 1536, 2048, 4096) |
-| `black-forest-labs/flux-1-schnell`     | Fast image generation (4 steps) | 1:1, 4:3, 3:4                         |
-| `black-forest-labs/flux-1-dev`         | High-quality image generation   | 1:1, 4:3, 3:4                         |
-| `black-forest-labs/flux-1-kontext-dev` | Context-aware image generation  | 1:1, 4:3, 3:4                         |
-| `qwen/qwen-image`                      | Text-to-image generation        | 1:1, 4:3, 3:4                         |
-| `qwen/qwen-image-edit`                 | Image editing (prompt-guided)   | 1:1, 4:3, 3:4                         |
-| `nano-banana-edit`                     | Image editing (multi-image)     | 1:1, 4:3, 3:4                         |
-| `google/nano-banana-pro-edit`          | Image editing (Gemini-powered)  | Uses resolution param (1k, 2k)        |
-| `pruna/p-image-t2i`                    | Pruna text-to-image             | 1:1, 16:9, 9:16, 4:3, 3:4, etc.       |
-| `pruna/p-image-edit`                   | Pruna image editing             | match_input_image, 1:1, 16:9, etc.    |
-
-**Note**: The provider uses strict validation for image parameters. Unsupported aspect ratios (like `16:9`, `9:16`, `3:2`, `2:3`) will throw an `InvalidArgumentError` with a clear message about supported alternatives.
+### Edit Image
 
-**Note:** This list is not complete. For a full list of all available models, see the [Runpod Public Endpoint Reference](https://docs.runpod.io/hub/public-endpoint-reference).
+For editing, pass reference images via `prompt.images` (recommended). The AI SDK normalizes `prompt.images` into `files` for the provider call.
 
-### Advanced Parameters
+#### Single reference image (1 input image)
 
 ```ts
+import { runpod } from '@runpod/ai-sdk-provider';
+import { experimental_generateImage as generateImage } from 'ai';
+
 const { image } = await generateImage({
-  model: runpod.imageModel('bytedance/seedream-3.0'),
-  prompt: 'A sunset over mountains',
-  size: '1328x1328',
-  seed: 42,
-  providerOptions: {
-    runpod: {
-      negative_prompt: 'blurry, low quality',
-      enable_safety_checker: true,
-    },
+  model: runpod.image('pruna/p-image-edit'),
+  prompt: {
+    text: 'Virtual staging: add modern Scandinavian furniture: a gray sofa, wooden coffee table, potted plants, and warm lighting',
+    images: ['https://image.runpod.ai/demo/empty-room.png'],
   },
+  aspectRatio: '16:9',
 });
 ```
 
-#### Modify Image
+#### Multiple reference images (4 input images)
 
-Transform existing images using text prompts.
+Note: Prior to v1.0.0, images were passed via `providerOptions.runpod.image` / `providerOptions.runpod.images`. This still works but `prompt.images` is now recommended.
 
 ```ts
-// Example: Transform existing image
-const { image } = await generateImage({
-  model: runpod.imageModel('black-forest-labs/flux-1-kontext-dev'),
-  prompt: 'Transform this into a cyberpunk style with neon lights',
-  aspectRatio: '1:1',
-  providerOptions: {
-    runpod: {
-      image: 'https://example.com/input-image.jpg',
-    },
-  },
-});
+import { runpod } from '@runpod/ai-sdk-provider';
+import { experimental_generateImage as generateImage } from 'ai';
 
-// Example: Using base64 encoded image
 const { image } = await generateImage({
-  model: runpod.imageModel('black-forest-labs/flux-1-kontext-dev'),
-  prompt: 'Make this image look like a painting',
-  providerOptions: {
-    runpod: {
-      image: 'data:image/png;base64,iVBORw0KGgoAAAANS...',
-    },
+  model: runpod.image('google/nano-banana-pro-edit'),
+  prompt: {
+    text: 'Combine these four robot musicians into an epic band photo on a concert stage with dramatic lighting',
+    images: [
+      'https://image.runpod.ai/demo/robot-drummer.png',
+      'https://image.runpod.ai/demo/robot-guitarist.png',
+      'https://image.runpod.ai/demo/robot-bassist.png',
+      'https://image.runpod.ai/demo/robot-singer.png',
+    ],
   },
 });
 ```
 
+### Examples
+
+Check out our [examples](https://github.com/runpod/examples/tree/main/ai-sdk/getting-started) for more code snippets on how to use all the different models.
+
+### Supported Models
+
+| Model ID                               | Type |
+| -------------------------------------- | ---- |
+| `pruna/p-image-t2i`                    | t2i  |
+| `pruna/p-image-edit`                   | edit |
+| `google/nano-banana-pro-edit`          | edit |
+| `bytedance/seedream-3.0`               | t2i  |
+| `bytedance/seedream-4.0`               | t2i  |
+| `bytedance/seedream-4.0-edit`          | edit |
+| `qwen/qwen-image`                      | t2i  |
+| `qwen/qwen-image-edit`                 | edit |
+| `nano-banana-edit`                     | edit |
+| `black-forest-labs/flux-1-schnell`     | t2i  |
+| `black-forest-labs/flux-1-dev`         | t2i  |
+| `black-forest-labs/flux-1-kontext-dev` | edit |
+
+For the full list of models, see the [Runpod Public Endpoint Reference](https://docs.runpod.io/hub/public-endpoint-reference).
+
+### Provider Options
+
+Additional options through `providerOptions.runpod` (supported options depend on the model):
+
+| Option                   | Type       | Default | Description                                                 |
+| ------------------------ | ---------- | ------- | ----------------------------------------------------------- |
+| `negative_prompt`        | `string`   | `""`    | What to avoid in the image (model-dependent)                |
+| `enable_safety_checker`  | `boolean`  | `true`  | Content safety filtering (model-dependent)                  |
+| `disable_safety_checker` | `boolean`  | `false` | Disable safety checker (Pruna)                              |
+| `aspect_ratio`           | `string`   | -       | Model-specific aspect ratio (Pruna: supports `custom`)      |
+| `image`                  | `string`   | -       | Legacy: Single input image URL/base64 (use `prompt.images`) |
+| `images`                 | `string[]` | -       | Legacy: Multiple input images (use `prompt.images`)         |
+| `resolution`             | `string`   | `"1k"`  | Output resolution: 1k, 2k, 4k (Nano Banana Pro)             |
+| `width` / `height`       | `number`   | -       | Custom dimensions (Pruna t2i, 256-1440; multiples of 16)    |
+| `num_inference_steps`    | `number`   | Auto    | Denoising steps (model-dependent)                           |
+| `guidance`               | `number`   | Auto    | Prompt adherence strength (model-dependent)                 |
+| `output_format`          | `string`   | `"png"` | Output format: png, jpg, jpeg, webp (model-dependent)       |
+| `maxPollAttempts`        | `number`   | `60`    | Max polling attempts                                        |
+| `pollIntervalMillis`     | `number`   | `5000`  | Polling interval (ms)                                       |
+
+**Example (providerOptions):**
+
 ```ts
-// Example: Combine multiple images using Nano Banana edit
 const { image } = await generateImage({
-  model: runpod.imageModel('nano-banana-edit'),
-  prompt:
-    'Combine these four images into a single realistic 3D character scene.',
-  // Defaults to 1:1; you can also set size: '1328x1328' or aspectRatio: '4:3'
+  model: runpod.image('bytedance/seedream-3.0'),
+  prompt: 'A sunset over mountains',
+  size: '1328x1328',
+  seed: 42,
   providerOptions: {
     runpod: {
-      images: [
-        'https://image.runpod.ai/uploads/0bz_xzhuLq/a2166199-5bd5-496b-b9ab-a8bae3f73bdc.jpg',
-        'https://image.runpod.ai/uploads/Yw86rhY6xi/2ff8435f-f416-4096-9a4d-2f8c838b2d53.jpg',
-        'https://image.runpod.ai/uploads/bpCCX9zLY8/3bc27605-6f9a-40ad-83e9-c29bed45fed9.jpg',
-        'https://image.runpod.ai/uploads/LPHEY6pyHp/f950ceb8-fafa-4800-bdf1-fd3fd684d843.jpg',
-      ],
+      negative_prompt: 'blurry, low quality',
       enable_safety_checker: true,
+      maxPollAttempts: 30,
+      pollIntervalMillis: 4000,
     },
   },
 });
 ```
 
-Check out our [examples](https://github.com/runpod/examples/tree/main/ai-sdk/getting-started) for more code snippets on how to use all the different models.
+### Model-specific Notes
+
+#### Pruna (p-image)
+
+Supported models: `pruna/p-image-t2i`, `pruna/p-image-edit`
+
+- **Text-to-image**: supports standard `aspectRatio` values; for custom dimensions, set `providerOptions.runpod.aspect_ratio = 'custom'` and provide `width`/`height`.
+- **Edit image**: supports 1–5 input images via `prompt.images` (recommended) or `files`.
 
-### Advanced Configuration
+**Example: Custom Dimensions (t2i)**
 
 ```ts
-// Full control over generation parameters
 const { image } = await generateImage({
-  model: runpod.imageModel('black-forest-labs/flux-1-dev'),
-  prompt: 'A majestic dragon breathing fire in a medieval castle',
-  size: '1328x1328',
-  seed: 42, // For reproducible results
+  model: runpod.image('pruna/p-image-t2i'),
+  prompt: 'A robot',
   providerOptions: {
     runpod: {
-      negative_prompt: 'blurry, low quality, distorted, ugly, bad anatomy',
-      enable_safety_checker: true,
-      num_inference_steps: 50, // Higher quality (default: 28)
-      guidance: 3.5, // Stronger prompt adherence (default: 2)
-      output_format: 'png', // High quality format
-      // Polling settings for long generations
-      maxPollAttempts: 30,
-      pollIntervalMillis: 4000,
+      aspect_ratio: 'custom',
+      width: 512,
+      height: 768,
     },
   },
 });
+```
 
-// Fast generation with minimal steps
-const { image } = await generateImage({
-  model: runpod.imageModel('black-forest-labs/flux-1-schnell'),
-  prompt: 'A simple red apple',
-  aspectRatio: '1:1',
+#### Google (Nano Banana Pro)
+
+Supported model: `google/nano-banana-pro-edit`
+
+| Parameter                       | Supported Values                                                  | Notes                                |
+| :------------------------------ | :---------------------------------------------------------------- | :----------------------------------- |
+| `aspectRatio`                   | `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `3:2`, `2:3`, `21:9`, `9:21` | Standard AI SDK parameter            |
+| `resolution`                    | `1k`, `2k`, `4k`                                                  | Output resolution quality            |
+| `output_format`                 | `jpeg`, `png`, `webp`                                             | Output image format                  |
+| `prompt.images`                 | `string[]`                                                        | Recommended. Input image(s) to edit. |
+| `files`                         | `ImageModelV3File[]`                                              | Alternative (lower-level).           |
+| `providerOptions.runpod.images` | `string[]`                                                        | Legacy. Input image(s) to edit.      |
+
+## Speech Models
+
+Generate speech using the AI SDK's `experimental_generateSpeech` and `runpod.speech(...)`:
+
+```ts
+import { runpod } from '@runpod/ai-sdk-provider';
+import { experimental_generateSpeech as generateSpeech } from 'ai';
+
+const result = await generateSpeech({
+  model: runpod.speech('resembleai/chatterbox-turbo'),
+  text: 'Hello from Runpod.',
+});
+
+// Save to filesystem:
+import { writeFileSync } from 'fs';
+writeFileSync('speech.wav', result.audio.uint8Array);
+```
+
+**Returns:**
+
+- `result.audio` (`GeneratedAudioFile`)
+  - `result.audio.uint8Array` (binary audio)
+  - `result.audio.base64` (base64-encoded audio)
+  - `result.audio.mediaType` (e.g. `audio/wav`)
+  - `result.audio.format` (e.g. `wav`)
+- `result.warnings` (e.g. unsupported parameters)
+- `result.responses` (telemetry/debug metadata)
+- `result.providerMetadata.runpod`
+  - `audioUrl` (public URL to the generated audio)
+  - `cost` (if available)
+
+### Examples
+
+Check out our [examples](https://github.com/runpod/examples/tree/main/ai-sdk/getting-started) for more code snippets on how to use all the different models.
+
+### Supported Models
+
+- `resembleai/chatterbox-turbo`
+
+### `resembleai/chatterbox-turbo`
+
+#### Parameters
+
+| Parameter | Type     | Default  | Description                              |
+| --------- | -------- | -------- | ---------------------------------------- |
+| `text`    | `string` | -        | Required. The text to convert to speech. |
+| `voice`   | `string` | `"lucy"` | Built-in voice name (see list below).    |
+
+#### Provider Options
+
+Use `providerOptions.runpod` for model-specific parameters:
+
+| Option      | Type     | Default | Description                                 |
+| ----------- | -------- | ------- | ------------------------------------------- |
+| `voice_url` | `string` | -       | URL to audio file (5–10s) for voice cloning |
+| `voiceUrl`  | `string` | -       | Alias for `voice_url`                       |
+
+> Note: If `voice_url` is provided, the built-in `voice` is ignored.
+>
+> Note: This speech endpoint currently returns WAV only; `outputFormat` is ignored.
+
+#### Voices
+
+`voice` selects one of the built-in voices (default: `lucy`):
+
+```ts
+[
+  'aaron',
+  'abigail',
+  'anaya',
+  'andy',
+  'archer',
+  'brian',
+  'chloe',
+  'dylan',
+  'emmanuel',
+  'ethan',
+  'evelyn',
+  'gavin',
+  'gordon',
+  'ivan',
+  'laura',
+  'lucy',
+  'madison',
+  'marisol',
+  'meera',
+  'walter',
+];
+```
+
+#### Voice cloning (via URL)
+
+Use `providerOptions.runpod.voice_url` (or `voiceUrl`) to clone a voice from a short reference audio (5–10s):
+
+```ts
+const result = await generateSpeech({
+  model: runpod.speech('resembleai/chatterbox-turbo'),
+  text: 'Hello!',
   providerOptions: {
     runpod: {
-      num_inference_steps: 2, // Even faster (default: 4)
-      guidance: 10, // Higher guidance for simple prompts
-      output_format: 'jpg', // Smaller file size
+      voice_url: 'https://example.com/voice.wav',
     },
   },
 });
 ```
 
-### Provider Options
+#### Paralinguistic Tags
+
+Include these tags inline with your text to trigger realistic vocal expressions:
+
+| Tag              | Effect          |
+| ---------------- | --------------- |
+| `[clear throat]` | Throat clearing |
+| `[sigh]`         | Sighing         |
+| `[sush]`         | Shushing        |
+| `[cough]`        | Coughing        |
+| `[groan]`        | Groaning        |
+| `[sniff]`        | Sniffing        |
+| `[gasp]`         | Gasping         |
+| `[chuckle]`      | Chuckling       |
+| `[laugh]`        | Laughing        |
 
-Runpod image models support flexible provider options through the `providerOptions.runpod` object:
-
-| Option                   | Type       | Default | Description                                                              |
-| ------------------------ | ---------- | ------- | ------------------------------------------------------------------------ |
-| `negative_prompt`        | `string`   | `""`    | Text describing what you don't want in the image                         |
-| `enable_safety_checker`  | `boolean`  | `true`  | Enable content safety filtering                                          |
-| `disable_safety_checker` | `boolean`  | `false` | Disable safety checker (Pruna models)                                    |
-| `image`                  | `string`   | -       | Single input image: URL or base64 data URI (Flux Kontext)                |
-| `images`                 | `string[]` | -       | Multiple input images (e.g., for `nano-banana-edit` multi-image editing) |
-| `aspect_ratio`           | `string`   | `"1:1"` | Aspect ratio string (Pruna: "16:9", "match_input_image", etc.)           |
-| `resolution`             | `string`   | `"1k"`  | Output resolution (Nano Banana Pro: "1k", "2k")                          |
-| `num_inference_steps`    | `number`   | Auto    | Number of denoising steps (Flux: 4 for schnell, 28 for others)           |
-| `guidance`               | `number`   | Auto    | Guidance scale for prompt adherence (Flux: 7 for schnell, 2 for others)  |
-| `output_format`          | `string`   | `"png"` | Output image format ("png", "jpg", or "jpeg")                            |
-| `enable_base64_output`   | `boolean`  | `false` | Return base64 instead of URL (Nano Banana Pro)                           |
-| `enable_sync_mode`       | `boolean`  | `false` | Enable synchronous mode (some models)                                    |
-| `maxPollAttempts`        | `number`   | `60`    | Maximum polling attempts for async generation                            |
-| `pollIntervalMillis`     | `number`   | `5000`  | Polling interval in milliseconds (5 seconds)                             |
+```ts
+const result = await generateSpeech({
+  model: runpod.speech('resembleai/chatterbox-turbo'),
+  text: `[sigh] I can't believe it worked! [laugh] This is amazing.`,
+  voice: 'lucy',
+});
+```
 
 ## About Runpod
 

package/dist/index.d.mts

@@ -1,4 +1,4 @@
-import { LanguageModelV2, ImageModelV2 } from '@ai-sdk/provider';
+import { LanguageModelV3, ImageModelV3, SpeechModelV3 } from '@ai-sdk/provider';
 import { FetchFunction } from '@ai-sdk/provider-utils';
 export { OpenAICompatibleErrorData as RunpodErrorData } from '@ai-sdk/openai-compatible';
 import { z } from 'zod';
@@ -27,23 +27,35 @@ interface RunpodProvider {
     /**
   Creates a model for text generation.
   */
-    (modelId: string): LanguageModelV2;
+    (modelId: string): LanguageModelV3;
     /**
   Creates a chat model for text generation.
   */
-    chatModel(modelId: string): LanguageModelV2;
+    chatModel(modelId: string): LanguageModelV3;
     /**
   Creates a chat model for text generation.
   */
-    languageModel(modelId: string): LanguageModelV2;
+    languageModel(modelId: string): LanguageModelV3;
     /**
   Creates a completion model for text generation.
   */
-    completionModel(modelId: string): LanguageModelV2;
+    completionModel(modelId: string): LanguageModelV3;
     /**
   Creates an image model for image generation.
   */
-    imageModel(modelId: string): ImageModelV2;
+    imageModel(modelId: string): ImageModelV3;
+    /**
+  Creates an image model for image generation.
+  */
+    image(modelId: string): ImageModelV3;
+    /**
+  Creates a speech model for speech generation.
+  */
+    speechModel(modelId: string): SpeechModelV3;
+    /**
+  Creates a speech model for speech generation.
+  */
+    speech(modelId: string): SpeechModelV3;
 }
 declare function createRunpod(options?: RunpodProviderSettings): RunpodProvider;
 declare const runpod: RunpodProvider;

package/dist/index.d.ts

@@ -1,4 +1,4 @@
-import { LanguageModelV2, ImageModelV2 } from '@ai-sdk/provider';
+import { LanguageModelV3, ImageModelV3, SpeechModelV3 } from '@ai-sdk/provider';
 import { FetchFunction } from '@ai-sdk/provider-utils';
 export { OpenAICompatibleErrorData as RunpodErrorData } from '@ai-sdk/openai-compatible';
 import { z } from 'zod';
@@ -27,23 +27,35 @@ interface RunpodProvider {
     /**
   Creates a model for text generation.
   */
-    (modelId: string): LanguageModelV2;
+    (modelId: string): LanguageModelV3;
     /**
   Creates a chat model for text generation.
   */
-    chatModel(modelId: string): LanguageModelV2;
+    chatModel(modelId: string): LanguageModelV3;
     /**
   Creates a chat model for text generation.
   */
-    languageModel(modelId: string): LanguageModelV2;
+    languageModel(modelId: string): LanguageModelV3;
     /**
   Creates a completion model for text generation.
   */
-    completionModel(modelId: string): LanguageModelV2;
+    completionModel(modelId: string): LanguageModelV3;
     /**
   Creates an image model for image generation.
   */
-    imageModel(modelId: string): ImageModelV2;
+    imageModel(modelId: string): ImageModelV3;
+    /**
+  Creates an image model for image generation.
+  */
+    image(modelId: string): ImageModelV3;
+    /**
+  Creates a speech model for speech generation.
+  */
+    speechModel(modelId: string): SpeechModelV3;
+    /**
+  Creates a speech model for speech generation.
+  */
+    speech(modelId: string): SpeechModelV3;
 }
 declare function createRunpod(options?: RunpodProviderSettings): RunpodProvider;
 declare const runpod: RunpodProvider;