@ai-sdk/azure 3.0.21 → 3.0.23

package/CHANGELOG.md

@@ -1,5 +1,19 @@
 # @ai-sdk/azure
 
+## 3.0.23
+
+### Patch Changes
+
+- 1524271: chore: add skill information to README files
+- Updated dependencies [1524271]
+  - @ai-sdk/openai@3.0.22
+
+## 3.0.22
+
+### Patch Changes
+
+- 3988c08: docs: fix incorrect and outdated provider docs
+
 ## 3.0.21
 
 ### Patch Changes

package/README.md

@@ -10,6 +10,14 @@ The Azure provider is available in the `@ai-sdk/azure` module. You can install i
 npm i @ai-sdk/azure
 ```
 
+## Skill for Coding Agents
+
+If you use coding agents such as Claude Code or Cursor, we highly recommend adding the AI SDK skill to your repository:
+
+```shell
+npx skills add vercel/ai
+```
+
 ## Provider Instance
 
 You can import the default provider instance `azure` from `@ai-sdk/azure`:

package/dist/index.js

@@ -40,7 +40,7 @@ var azureOpenaiTools = {
 };
 
 // src/version.ts
-var VERSION = true ? "3.0.21" : "0.0.0-test";
+var VERSION = true ? "3.0.23" : "0.0.0-test";
 
 // src/azure-openai-provider.ts
 function createAzure(options = {}) {

package/dist/index.mjs

@@ -29,7 +29,7 @@ var azureOpenaiTools = {
 };
 
 // src/version.ts
-var VERSION = true ? "3.0.21" : "0.0.0-test";
+var VERSION = true ? "3.0.23" : "0.0.0-test";
 
 // src/azure-openai-provider.ts
 function createAzure(options = {}) {

package/docs/04-azure.mdx

@@ -1029,3 +1029,67 @@ The following provider options are available:
 | `whisper-1`              | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
 | `gpt-4o-mini-transcribe` | <Check size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
 | `gpt-4o-transcribe`      | <Check size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+
+## Speech Models
+
+You can create models that call the Azure OpenAI speech API using the `.speech()` factory method.
+
+The first argument is your deployment name for the text-to-speech model (e.g., `tts-1`).
+
+```ts
+const model = azure.speech('your-tts-deployment-name');
+```
+
+### Example
+
+```ts
+import { azure } from '@ai-sdk/azure';
+import { experimental_generateSpeech as generateSpeech } from 'ai';
+
+const result = await generateSpeech({
+  model: azure.speech('your-tts-deployment-name'),
+  text: 'Hello, world!',
+  voice: 'alloy', // OpenAI voice ID
+});
+```
+
+You can also pass additional provider-specific options using the `providerOptions` argument:
+
+```ts
+import { azure } from '@ai-sdk/azure';
+import { experimental_generateSpeech as generateSpeech } from 'ai';
+
+const result = await generateSpeech({
+  model: azure.speech('your-tts-deployment-name'),
+  text: 'Hello, world!',
+  voice: 'alloy',
+  providerOptions: {
+    openai: {
+      speed: 1.2,
+    },
+  },
+});
+```
+
+The following provider options are available:
+
+- **instructions** _string_
+  Control the voice of your generated audio with additional instructions e.g. "Speak in a slow and steady tone".
+  Does not work with `tts-1` or `tts-1-hd`.
+  Optional.
+
+- **speed** _number_
+  The speed of the generated audio.
+  Select a value from 0.25 to 4.0.
+  Defaults to 1.0.
+  Optional.
+
+### Model Capabilities
+
+Azure OpenAI supports TTS models through deployments. The capabilities depend on which model version your deployment is using:
+
+| Model Version     | Instructions        |
+| ----------------- | ------------------- |
+| `tts-1`           | <Cross size={18} /> |
+| `tts-1-hd`        | <Cross size={18} /> |
+| `gpt-4o-mini-tts` | <Check size={18} /> |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ai-sdk/azure",
-  "version": "3.0.21",
+  "version": "3.0.23",
   "license": "Apache-2.0",
   "sideEffects": false,
   "main": "./dist/index.js",
@@ -29,9 +29,9 @@
     }
   },
   "dependencies": {
-    "@ai-sdk/openai": "3.0.21",
     "@ai-sdk/provider": "3.0.5",
-    "@ai-sdk/provider-utils": "4.0.10"
+    "@ai-sdk/provider-utils": "4.0.10",
+    "@ai-sdk/openai": "3.0.22"
   },
   "devDependencies": {
     "@types/node": "20.17.24",