Add Sarvam LLM, update Sarvam STT models, expose usage_info on run detail (#351)

* Add Sarvam LLM provider, update Sarvam STT models, expose usage_info on run detail.
Depends on pipecat PR dograh-hq/pipecat#43 for STT string language support.
Submodule bump will follow after that merges.

* test: cover Sarvam STT language mapping; link Sarvam docs

---------

Co-authored-by: Sabiha Khan <sabihak89@gmail.com>

api/services/configuration/options/__init__.py

@@ -16,6 +16,9 @@ from .google import (
 )
 from .sarvam import (
     SARVAM_LANGUAGES,
+    SARVAM_LLM_MODELS,
+    SARVAM_STT_LANGUAGES_V25,
+    SARVAM_STT_LANGUAGES_V3,
     SARVAM_STT_MODELS,
     SARVAM_TTS_MODELS,
     SARVAM_V2_VOICES,
@@ -41,6 +44,9 @@ __all__ = [
     "GOOGLE_VERTEX_REALTIME_MODELS",
     "GOOGLE_VERTEX_REALTIME_VOICES",
     "SARVAM_LANGUAGES",
+    "SARVAM_LLM_MODELS",
+    "SARVAM_STT_LANGUAGES_V25",
+    "SARVAM_STT_LANGUAGES_V3",
     "SARVAM_STT_MODELS",
     "SARVAM_TTS_MODELS",
     "SARVAM_V2_VOICES",

api/services/configuration/options/sarvam.py

@@ -63,4 +63,38 @@ SARVAM_LANGUAGES = (
     "te-IN",
     "as-IN",
 )
-SARVAM_STT_MODELS = ("saarika:v2.5", "saaras:v2")
+SARVAM_STT_MODELS = ("saarika:v2.5", "saaras:v3")
+# saarika:v2.5 language codes (unknown = auto-detect)
+SARVAM_STT_LANGUAGES_V25 = (
+    "unknown",
+    "hi-IN",
+    "bn-IN",
+    "gu-IN",
+    "kn-IN",
+    "ml-IN",
+    "mr-IN",
+    "od-IN",
+    "pa-IN",
+    "ta-IN",
+    "te-IN",
+    "en-IN",
+)
+# saaras:v3 adds these regional languages on top of the v2.5 set. Full list: https://docs.sarvam.ai/api-reference-docs/speech-to-text/transcribe
+SARVAM_STT_LANGUAGES_V3 = SARVAM_STT_LANGUAGES_V25 + (
+    "as-IN",
+    "ur-IN",
+    "ne-IN",
+    "kok-IN",
+    "ks-IN",
+    "sd-IN",
+    "sa-IN",
+    "sat-IN",
+    "mni-IN",
+    "brx-IN",
+    "mai-IN",
+    "doi-IN",
+)
+SARVAM_LLM_MODELS = (
+    "sarvam-30b",
+    "sarvam-105b",
+)

api/services/configuration/registry.py

@@ -22,6 +22,9 @@ from api.services.configuration.options import (
     GOOGLE_VERTEX_REALTIME_MODELS,
     GOOGLE_VERTEX_REALTIME_VOICES,
     SARVAM_LANGUAGES,
+    SARVAM_LLM_MODELS,
+    SARVAM_STT_LANGUAGES_V25,
+    SARVAM_STT_LANGUAGES_V3,
     SARVAM_STT_MODELS,
     SARVAM_TTS_MODELS,
     SARVAM_V2_VOICES,
@@ -89,7 +92,7 @@ class BaseServiceConfiguration(BaseModel):
         ServiceProviders.ULTRAVOX_REALTIME,
         ServiceProviders.GOOGLE_REALTIME,
         ServiceProviders.GOOGLE_VERTEX_REALTIME,
-        # ServiceProviders.SARVAM,
+        ServiceProviders.SARVAM,
     ]
     api_key: str | list[str]
 
@@ -472,6 +475,29 @@ class MiniMaxLLMConfiguration(BaseLLMConfiguration):
     )
 
 
+@register_llm
+class SarvamLLMConfiguration(BaseLLMConfiguration):
+    model_config = SARVAM_PROVIDER_MODEL_CONFIG
+    provider: Literal[ServiceProviders.SARVAM] = ServiceProviders.SARVAM
+    model: str = Field(
+        default="sarvam-30b",
+        description=(
+            "Sarvam chat model. Use sarvam-30b for low-latency voice agents; "
+            "sarvam-105b for complex multi-step reasoning."
+        ),
+        json_schema_extra={"examples": SARVAM_LLM_MODELS, "allow_custom_input": True},
+    )
+    temperature: float = Field(
+        default=0.5,
+        ge=0.0,
+        le=2.0,
+        description=(
+            "Sampling temperature. Sarvam recommends 0.5 for balanced "
+            "conversational responses."
+        ),
+    )
+
+
 OPENAI_REALTIME_MODELS = ["gpt-realtime-2"]
 OPENAI_REALTIME_VOICES = [
     "alloy",
@@ -661,6 +687,7 @@ LLMConfig = Annotated[
         AWSBedrockLLMConfiguration,
         SpeachesLLMConfiguration,
         MiniMaxLLMConfiguration,
+        SarvamLLMConfiguration,
     ],
     Field(discriminator="provider"),
 ]
@@ -1129,13 +1156,24 @@ class SarvamSTTConfiguration(BaseSTTConfiguration):
     provider: Literal[ServiceProviders.SARVAM] = ServiceProviders.SARVAM
     model: str = Field(
         default="saarika:v2.5",
-        description="Sarvam STT model.",
+        description=(
+            "Sarvam STT model. saarika:v2.5 transcribes in the spoken language; "
+            "saaras:v3 is the recommended model with flexible output modes."
+        ),
         json_schema_extra={"examples": SARVAM_STT_MODELS},
     )
     language: str = Field(
-        default="hi-IN",
-        description="BCP-47 Indian-language code.",
-        json_schema_extra={"examples": SARVAM_LANGUAGES},
+        default="unknown",
+        description=(
+            "BCP-47 language code. Use unknown for automatic language detection."
+        ),
+        json_schema_extra={
+            "examples": SARVAM_STT_LANGUAGES_V25,
+            "model_options": {
+                "saarika:v2.5": SARVAM_STT_LANGUAGES_V25,
+                "saaras:v3": SARVAM_STT_LANGUAGES_V3,
+            },
+        },
     )
 
 

api/services/pipecat/service_factory.py

@@ -47,6 +47,7 @@ from pipecat.services.openai.stt import (
 from pipecat.services.openai.tts import OpenAITTSService, OpenAITTSSettings
 from pipecat.services.openrouter.llm import OpenRouterLLMService, OpenRouterLLMSettings
 from pipecat.services.rime.tts import RimeTTSService, RimeTTSSettings
+from pipecat.services.sarvam.llm import SarvamLLMService, SarvamLLMSettings
 from pipecat.services.sarvam.stt import SarvamSTTService, SarvamSTTSettings
 from pipecat.services.sarvam.tts import SarvamTTSService, SarvamTTSSettings
 from pipecat.services.speaches.llm import SpeachesLLMService, SpeachesLLMSettings
@@ -158,7 +159,7 @@ def create_stt_service(
             sample_rate=audio_config.transport_in_sample_rate,
         )
     elif user_config.stt.provider == ServiceProviders.SARVAM.value:
-        # Map Sarvam language code to pipecat Language enum
+        language = getattr(user_config.stt, "language", None)
         language_mapping = {
             "bn-IN": Language.BN_IN,
             "gu-IN": Language.GU_IN,
@@ -172,9 +173,18 @@ def create_stt_service(
             "od-IN": Language.OR_IN,
             "en-IN": Language.EN_IN,
             "as-IN": Language.AS_IN,
+            "ur-IN": Language.UR_IN,
+            "kok-IN": Language.KOK_IN,
+            "mai-IN": Language.MAI_IN,
+            "sd-IN": Language.SD_IN,
         }
-        language = getattr(user_config.stt, "language", None)
-        pipecat_language = language_mapping.get(language, Language.HI_IN)
+        if not language or language == "unknown":
+            pipecat_language = None
+        elif language in language_mapping:
+            pipecat_language = language_mapping[language]
+        else:
+            # Unmapped BCP-47 codes pass through; Sarvam accepts them per https://docs.sarvam.ai/api-reference-docs/speech-to-text/transcribe
+            pipecat_language = language
         return SarvamSTTService(
             api_key=user_config.stt.api_key,
             settings=SarvamSTTSettings(
@@ -604,6 +614,14 @@ def create_llm_service_from_provider(
                 temperature=temperature if temperature is not None else 1.0,
             ),
         )
+    elif provider == ServiceProviders.SARVAM.value:
+        return SarvamLLMService(
+            api_key=api_key,
+            settings=SarvamLLMSettings(
+                model=model,
+                temperature=temperature if temperature is not None else 0.5,
+            ),
+        )
     else:
         raise HTTPException(status_code=400, detail=f"Invalid LLM provider {provider}")
 
@@ -756,5 +774,7 @@ def create_llm_service(user_config):
     elif provider == ServiceProviders.MINIMAX.value:
         kwargs["base_url"] = user_config.llm.base_url
         kwargs["temperature"] = user_config.llm.temperature
+    elif provider == ServiceProviders.SARVAM.value:
+        kwargs["temperature"] = user_config.llm.temperature
 
     return create_llm_service_from_provider(provider, model, api_key, **kwargs)

api/services/pricing/run_usage_response.py

@@ -0,0 +1,13 @@
+"""Format workflow run usage for public API responses."""
+
+
+def format_public_usage_info(usage_info: dict | None) -> dict | None:
+    if not usage_info:
+        return None
+
+    return {
+        "llm": usage_info.get("llm") or {},
+        "tts": usage_info.get("tts") or {},
+        "stt": usage_info.get("stt") or {},
+        "call_duration_seconds": usage_info.get("call_duration_seconds"),
+    }