sarvam-ai-sdk 0.1.2 → 0.1.3

package/README.md

@@ -65,7 +65,7 @@ import { experimental_transcribe as transcribe } from "ai";
 import { readFile } from "fs/promises";
 
 const { text } = await transcribe({
-    model: sarvam.transcription("saarika:v2.5", "ml-IN")
+    model: sarvam.transcription("saarika:v2.5", "ml-IN"),
     audio: await readFile("./src/transcript-test.wav"),
 });
 
@@ -214,6 +214,35 @@ const { object } = await generateObject({
 console.log(object);
 ```
 
+## All APIs
+
+```ts
+import { sarvam } from "sarvam-ai-sdk";
+
+// Text-to-Text + Chat Completion
+sarvam("sarvam-105b");
+sarvam.languageModel("sarvam-30b");
+
+// Text-to-Text + Transliteration
+sarvam.transliterate({ from: "en-IN", to: "ml-IN" });
+
+// Text-to-Text + Translation
+sarvam.translation({ from: "en-IN", to: "ml-IN" });
+
+// Text-to-Text + Language identification
+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");
+```
+
+
 ## Documentation
 
 Please check out the **[Sarvam provider documentation](https://v4.ai-sdk.dev/providers/ai-sdk-providers/sarvam)** and **[Sarvam API documentation](https://docs.sarvam.ai)** for more information.

package/dist/index.d.mts

@@ -52,7 +52,7 @@ declare const SarvamLanguageCodeSchema: z.ZodEnum<["hi-IN", "bn-IN", "kn-IN", "m
 
 type SarvamSpeechModelId = "bulbul:v2" | "bulbul:v3" | (string & {});
 type SarvamSpeechVoices = z.infer<typeof SpeakerSchema>;
-declare const SpeakerSchema: z.ZodDefault<z.ZodEnum<["abhilash", "karun", "hitesh", "anushka", "manisha", "vidya", "arya", "shubh", "aditya", "rahul", "rohan", "amit", "dev", "ratan", "varun", "manan", "sumit", "kabir", "aayan", "ashutosh", "advait", "anand", "tarun", "sunny", "mani", "gokul", "vijay", "mohit", "rehan", "soham", "ritu", "priya", "neha", "pooja", "simran", "kavya", "ishita", "shreya", "roopa", "amelia", "sophia", "tanya", "shruti", "suhani", "kavitha", "rupali"]>>;
+declare const SpeakerSchema: z.ZodEnum<["abhilash", "karun", "hitesh", "anushka", "manisha", "vidya", "arya", "shubh", "aditya", "rahul", "rohan", "amit", "dev", "ratan", "varun", "manan", "sumit", "kabir", "aayan", "ashutosh", "advait", "anand", "tarun", "sunny", "mani", "gokul", "vijay", "mohit", "rehan", "soham", "ritu", "priya", "neha", "pooja", "simran", "kavya", "ishita", "shreya", "roopa", "amelia", "sophia", "tanya", "shruti", "suhani", "kavitha", "rupali"]>;
 /**
  * Configuration settings for Sarvam Text-to-Speech API.
  *
@@ -111,6 +111,37 @@ type SarvamSpeechSettings = {
      * @example false (Disable preprocessing)
      */
     enable_preprocessing?: boolean;
+    /**
+     * Specifies the audio codec for the output audio file.
+     * Different codecs offer various compression and quality characteristics.
+     */
+    output_audio_codec?: "mp3" | "linear16" | "mulaw" | "alaw" | "opus" | "flac" | "aac" | "wav";
+    /**
+     * Temperature controls how much randomness and expressiveness the TTS model uses while generating speech.
+     * Lower values produce more stable and consistent output,
+     * while higher values sound more expressive but may introduce artifacts or errors.
+     *
+     * Any number inbetween 0.01 - 2
+     * @default 0.6
+     *
+     * Note: This parameter is only supported for bulbul:v3. It has no effect on bulbul:v2.
+     */
+    temperature?: number;
+    /**
+     * The ID of a pronunciation dictionary to apply during synthesis.
+     * When provided, matching words in the input text will be replaced with their custom pronunciations before generating speech.
+     *
+     * Only supported by bulbul:v3.
+     */
+    dict_id?: string;
+    /**
+     * Enable caching for the request. When enabled, identical requests will return cached audio instead of regenerating.
+     *
+     * @default false
+     *
+     * Currently in beta and only available for bulbul:v1 and bulbul:v2 models.
+     */
+    enable_cached_responses?: boolean;
 };
 
 type SarvamTranscriptionModelId = "saaras:v3" | "saarika:v2.5" | (string & {});

package/dist/index.d.ts

@@ -52,7 +52,7 @@ declare const SarvamLanguageCodeSchema: z.ZodEnum<["hi-IN", "bn-IN", "kn-IN", "m
 
 type SarvamSpeechModelId = "bulbul:v2" | "bulbul:v3" | (string & {});
 type SarvamSpeechVoices = z.infer<typeof SpeakerSchema>;
-declare const SpeakerSchema: z.ZodDefault<z.ZodEnum<["abhilash", "karun", "hitesh", "anushka", "manisha", "vidya", "arya", "shubh", "aditya", "rahul", "rohan", "amit", "dev", "ratan", "varun", "manan", "sumit", "kabir", "aayan", "ashutosh", "advait", "anand", "tarun", "sunny", "mani", "gokul", "vijay", "mohit", "rehan", "soham", "ritu", "priya", "neha", "pooja", "simran", "kavya", "ishita", "shreya", "roopa", "amelia", "sophia", "tanya", "shruti", "suhani", "kavitha", "rupali"]>>;
+declare const SpeakerSchema: z.ZodEnum<["abhilash", "karun", "hitesh", "anushka", "manisha", "vidya", "arya", "shubh", "aditya", "rahul", "rohan", "amit", "dev", "ratan", "varun", "manan", "sumit", "kabir", "aayan", "ashutosh", "advait", "anand", "tarun", "sunny", "mani", "gokul", "vijay", "mohit", "rehan", "soham", "ritu", "priya", "neha", "pooja", "simran", "kavya", "ishita", "shreya", "roopa", "amelia", "sophia", "tanya", "shruti", "suhani", "kavitha", "rupali"]>;
 /**
  * Configuration settings for Sarvam Text-to-Speech API.
  *
@@ -111,6 +111,37 @@ type SarvamSpeechSettings = {
      * @example false (Disable preprocessing)
      */
     enable_preprocessing?: boolean;
+    /**
+     * Specifies the audio codec for the output audio file.
+     * Different codecs offer various compression and quality characteristics.
+     */
+    output_audio_codec?: "mp3" | "linear16" | "mulaw" | "alaw" | "opus" | "flac" | "aac" | "wav";
+    /**
+     * Temperature controls how much randomness and expressiveness the TTS model uses while generating speech.
+     * Lower values produce more stable and consistent output,
+     * while higher values sound more expressive but may introduce artifacts or errors.
+     *
+     * Any number inbetween 0.01 - 2
+     * @default 0.6
+     *
+     * Note: This parameter is only supported for bulbul:v3. It has no effect on bulbul:v2.
+     */
+    temperature?: number;
+    /**
+     * The ID of a pronunciation dictionary to apply during synthesis.
+     * When provided, matching words in the input text will be replaced with their custom pronunciations before generating speech.
+     *
+     * Only supported by bulbul:v3.
+     */
+    dict_id?: string;
+    /**
+     * Enable caching for the request. When enabled, identical requests will return cached audio instead of regenerating.
+     *
+     * @default false
+     *
+     * Currently in beta and only available for bulbul:v1 and bulbul:v2 models.
+     */
+    enable_cached_responses?: boolean;
 };
 
 type SarvamTranscriptionModelId = "saaras:v3" | "saarika:v2.5" | (string & {});

package/dist/index.js

@@ -767,6 +767,7 @@ var sarvamChatChunkSchema = import_zod2.z.union([
 
 // src/sarvam-speech-model.ts
 var import_provider_utils5 = require("@ai-sdk/provider-utils");
+var import_zod4 = require("zod");
 
 // src/sarvam-speech-settings.ts
 var import_zod3 = require("zod");
@@ -821,7 +822,17 @@ var SpeakerSchema = import_zod3.z.enum([
   "suhani",
   "kavitha",
   "rupali"
-]).default("shubh");
+]);
+var outputAudioCodecSchema = import_zod3.z.enum([
+  "mp3",
+  "linear16",
+  "mulaw",
+  "alaw",
+  "opus",
+  "flac",
+  "aac",
+  "wav"
+]);
 var SarvamProviderOptionsSchema = import_zod3.z.object({
   speaker: SpeakerSchema,
   pitch: import_zod3.z.number().min(-0.75).max(0.75).default(0),
@@ -833,11 +844,14 @@ var SarvamProviderOptionsSchema = import_zod3.z.object({
     import_zod3.z.literal(22050),
     import_zod3.z.literal(24e3)
   ]).default(22050),
-  enable_preprocessing: import_zod3.z.boolean().default(false)
+  enable_preprocessing: import_zod3.z.boolean().default(false),
+  output_audio_codec: outputAudioCodecSchema.optional(),
+  temperature: import_zod3.z.number().min(0.01).max(2).default(0.6),
+  dict_id: import_zod3.z.string().optional(),
+  enable_cached_responses: import_zod3.z.boolean().default(false)
 }).partial();
 
 // src/sarvam-speech-model.ts
-var import_zod4 = require("zod");
 var SarvamSpeechModel = class {
   constructor(modelId, languageCode, config) {
     this.modelId = modelId;
@@ -852,7 +866,7 @@ var SarvamSpeechModel = class {
     text,
     voice,
     outputFormat = "wav",
-    // speed,
+    speed,
     // instructions,
     providerOptions
   }) {
@@ -868,7 +882,6 @@ var SarvamSpeechModel = class {
       schema: SarvamProviderOptionsSchema
     });
     const getSpeaker = () => {
-      if (sarvamOptions == null ? void 0 : sarvamOptions.speaker) return sarvamOptions.speaker;
       if (voice) {
         return SpeakerSchema.parse(voice);
       }
@@ -884,32 +897,27 @@ var SarvamSpeechModel = class {
       model: this.modelId,
       text,
       target_language_code: this.languageCode,
-      speaker: getSpeaker()
-      // response_format: "wav",
-      // speed,
-      // instructions,
+      speaker: getSpeaker(),
+      pace: speed
     };
     if (outputFormat) {
-      if (["mp3", "opus", "aac", "flac", "wav", "pcm"].includes(
-        outputFormat
-      )) {
-        requestBody.response_format = outputFormat;
+      const of = outputAudioCodecSchema.safeParse(outputFormat);
+      if (of.success) {
+        requestBody.output_audio_codec = of.data;
       } else {
         warnings.push({
           type: "unsupported-setting",
           setting: "outputFormat",
-          details: `Unsupported output format: ${outputFormat}. Using mp3 instead.`
+          details: `Unsupported output format: ${outputFormat}. Using wav instead.`
         });
       }
     }
     if (sarvamOptions) {
-      const speechModelOptions = {};
-      for (const key in speechModelOptions) {
-        const value = speechModelOptions[key];
+      Object.entries(sarvamOptions).forEach(([key, value]) => {
         if (value !== void 0) {
           requestBody[key] = value;
         }
-      }
+      });
     }
     return {
       requestBody,
@@ -987,7 +995,6 @@ var SarvamTranscriptionModel = class {
     mediaType,
     providerOptions
   }) {
-    var _a;
     const warnings = [];
     const sarvamOptions = (0, import_provider_utils6.parseProviderOptions)({
       provider: "sarvam",
@@ -1003,23 +1010,13 @@ var SarvamTranscriptionModel = class {
     const blob = audio instanceof Blob ? audio : new Blob([audio], { type: mediaType });
     formData.append("file", blob);
     formData.append("model", this.modelId);
+    formData.append("language_code", this.languageCode);
     if (sarvamOptions) {
-      formData.append("mode", (_a = sarvamOptions.mode) != null ? _a : "transcribe");
-      formData.append("language_code", this.languageCode);
-      formData.append(
-        "with_timestamps",
-        sarvamOptions.with_timestamps ? "true" : "false"
-      );
-      formData.append(
-        "with_diarization",
-        sarvamOptions.with_diarization ? "true" : "false"
-      );
-      if (sarvamOptions.num_speakers !== null && sarvamOptions.num_speakers !== void 0) {
-        formData.append(
-          "num_speakers",
-          sarvamOptions.num_speakers.toString()
-        );
-      }
+      Object.entries(sarvamOptions).forEach(([key, value]) => {
+        if (value) {
+          formData.append(key, String(value));
+        }
+      });
     }
     return {
       formData,