sarvam-ai-sdk 0.2.0-beta → 0.3.0

package/README.md

@@ -1,6 +1,10 @@
+<a href="https://github.com/rajatsandeepsen/sarvam-ai-sdk">
+    <img alt="cover" src="https://github.com/rajatsandeepsen/sarvam-ai-sdk/blob/master/cover.png?raw=true" />
+</a>
+
 # AI SDK - Sarvam Provider
 
-The **[Sarvam provider](https://v5.ai-sdk.dev/providers/ai-sdk-providers/sarvam)** for the [AI SDK](https://v5.ai-sdk.dev/docs)
+The **[Sarvam provider](https://v6.ai-sdk.dev/providers/community-providers/sarvam)** for the [AI SDK](https://v6.ai-sdk.dev/docs)
 contains language model support for the Sarvam chat completion, Text-to-Speech and Speech-to-Text APIs.
 
 ## Setup
@@ -8,11 +12,11 @@ contains language model support for the Sarvam chat completion, Text-to-Speech a
 The **[Sarvam](http://sarvam.ai)** provider is available in the `sarvam-ai-sdk` module. You can install it with
 
 ```bash
-npm i sarvam-ai-sdk ai@5
+npm i sarvam-ai-sdk ai@6
 ```
 
 > [!WARNING]
-> This package only works with Vercel AI-SDK v5, not v6 or latest v7. Make sure to install `ai@5` in your project.
+> This package only works with Vercel AI-SDK v6, not v7. Make sure to install `ai@6` in your project.
 
 ## Provider Instance
 
@@ -64,19 +68,6 @@ import { sarvam } from "sarvam-ai-sdk";
 import { experimental_transcribe as transcribe } from "ai";
 import { readFile } from "fs/promises";
 
-const { text } = await transcribe({
-    model: sarvam.transcription("saarika:v2.5", "ml-IN"),
-    audio: await readFile("./src/transcript-test.wav"),
-});
-
-console.log(text); // പാചകം തുടരും സുഹൃത്തുക്കളെ
-```
-
-```ts
-import { sarvam } from "sarvam-ai-sdk";
-import { experimental_transcribe as transcribe } from "ai";
-import { readFile } from "fs/promises";
-
 const { text } = await transcribe({
     model: sarvam.transcription("saaras:v3", "en-IN"),
     audio: await readFile("./src/transcript-test.wav"),
@@ -85,24 +76,9 @@ const { text } = await transcribe({
 console.log(text); // Pachakam thudaroo, suhruthukkale.
 ```
 
-## Speech-to-Text-Translate
-
-```ts
-import { sarvam } from "sarvam-ai-sdk";
-import { experimental_transcribe as transcribe } from "ai";
-import { readFile } from "fs/promises";
-
-const result = await transcribe({
-    model: sarvam.speechTranslation("saaras:v2.5"),
-    audio: await readFile("./src/transcript-test.wav"),
-});
-
-console.log(result.text); // Cooking continues, my friends
-```
-
 ## Translation
 
-> NB: Only transliterates `prompt` and `role:user` messages, not `role:system` not `role:assistant`.
+> NB: Only translates `prompt` and `role:user` messages, not `role:system` not `role:assistant`.
 
 ```ts
 import { sarvam } from "sarvam-ai-sdk";
@@ -228,14 +204,11 @@ sarvam.languageIdentification();
 // Text-to-Speech
 sarvam.speech("bulbul:v3", "ml-IN");
 
-// Speech-to-Text + Transcribe to same language
-sarvam.transcription("saarika:v2.5");
-
-// Speech-to-Text + Translate to English
-sarvam.speechTranslation("saaras:v3");
+// Speech-to-Text
+sarvam.transcription("saaras:v3");
 ```
 
 
 ## Documentation
 
-Please check out the **[Sarvam provider documentation](https://v5.ai-sdk.dev/providers/ai-sdk-providers/sarvam)** and **[Sarvam API documentation](https://docs.sarvam.ai)** for more information.
+Please check out the **[Sarvam provider documentation](https://v6.ai-sdk.dev/providers/community-providers/sarvam)** and **[Sarvam API documentation](https://docs.sarvam.ai)** for more information.