SDK regeneration

docs/reference/vendors.md

@@ -336,6 +336,7 @@ Use `turn_detection.language` for Agora interaction language; it defaults to `en
 | `api_key` | `str` | BYOK only | `None` | Deepgram API key. Optional only for Agora-managed `nova-2` and `nova-3`. |
 | `model` | `str` | No | `None` | Model (e.g., `nova-2`) |
 | `language` | `str` | No | `None` | Language code (e.g., `en-US`) |
+| `interaction_language` | `str` | No | `None` | Agora `asr.language` override |
 | `smart_format` | `bool` | No | `None` | Enable smart formatting |
 | `punctuation` | `bool` | No | `None` | Enable punctuation |
 | `additional_params` | `Dict[str, Any]` | No | `None` | Additional parameters |

src/agora_agent/agentkit/agent.py

@@ -57,6 +57,8 @@
 from ..agents.types.start_agents_request_properties_filler_words_content_static_config import StartAgentsRequestPropertiesFillerWordsContentStaticConfig
 from ..agents.types.start_agents_request_properties_filler_words_content_static_config_selection_rule import StartAgentsRequestPropertiesFillerWordsContentStaticConfigSelectionRule
 from ..types.tts import Tts
+from ..agents.types.start_agents_request_properties_filler_words_content_static_config_selection_rule import StartAgentsRequestPropertiesFillerWordsContentStaticConfigSelectionRule
+from ..types.tts import Tts
 from ..types.asr import Asr
 from ..types.llm import Llm
 from ..types.llm_style import LlmStyle as GeneratedLlmStyle
@@ -536,6 +538,23 @@ def with_audio_scenario(self, audio_scenario: ParametersAudioScenario) -> "Agent
             )
         return new_agent
 
+    def with_audio_scenario(self, audio_scenario: ParametersAudioScenario) -> "Agent":
+        """Returns a new Agent with the specified RTC audio scenario."""
+        new_agent = self._clone()
+        if new_agent._parameters is None:
+            new_agent._parameters = StartAgentsRequestPropertiesParameters(audio_scenario=audio_scenario)
+        elif isinstance(new_agent._parameters, dict):
+            new_agent._parameters = typing.cast(
+                SessionParamsInput,
+                {**new_agent._parameters, "audio_scenario": audio_scenario},
+            )
+        else:
+            new_agent._parameters = self._copy_model_update(
+                new_agent._parameters,
+                {"audio_scenario": audio_scenario},
+            )
+        return new_agent
+
     def with_failure_message(self, message: str) -> "Agent":
         """Deprecated. Configure the failure message on the LLM or MLLM vendor instead."""
         new_agent = self._clone()

src/agora_agent/agentkit/agent_session.py

@@ -24,6 +24,7 @@
     is_generic_avatar,
     is_heygen_avatar,
     is_live_avatar_avatar,
+    is_rtc_avatar,
     validate_avatar_config,
     validate_tts_sample_rate,
 )

src/agora_agent/agentkit/vendors/avatar.py

@@ -177,6 +177,49 @@ def to_config(self) -> Dict[str, Any]:
         return {"enable": enable, "vendor": "generic", "params": params}
 
 
+class GenericAvatarOptions(BaseModel):
+    model_config = ConfigDict(extra="forbid")
+
+    api_key: str = Field(..., description="Generic avatar provider API key")
+    api_base_url: str = Field(..., description="Avatar provider API base URL")
+    avatar_id: str = Field(..., description="Avatar ID")
+    agora_uid: str = Field(..., description="Agora UID for the avatar video stream")
+    agora_appid: Optional[str] = Field(default=None, description="Agora App ID; filled by AgentSession when omitted")
+    agora_token: Optional[str] = Field(default=None, description="RTC token; generated by AgentSession when omitted")
+    agora_channel: Optional[str] = Field(default=None, description="Agora channel; filled by AgentSession when omitted")
+    enable: Optional[bool] = Field(default=None, description="Enable avatar (default: true)")
+    additional_params: Optional[Dict[str, Any]] = Field(default=None, description="Additional vendor-specific parameters")
+
+
+class GenericAvatar(BaseAvatar):
+    def __init__(self, **kwargs: Any):
+        self.options = GenericAvatarOptions(**kwargs)
+
+    @property
+    def required_sample_rate(self) -> int:
+        return 0
+
+    def to_config(self) -> Dict[str, Any]:
+        params: Dict[str, Any] = {
+            "api_key": self.options.api_key,
+            "api_base_url": self.options.api_base_url,
+            "avatar_id": self.options.avatar_id,
+            "agora_uid": self.options.agora_uid,
+        }
+
+        if self.options.agora_appid is not None:
+            params["agora_appid"] = self.options.agora_appid
+        if self.options.agora_token is not None:
+            params["agora_token"] = self.options.agora_token
+        if self.options.agora_channel is not None:
+            params["agora_channel"] = self.options.agora_channel
+        if self.options.additional_params is not None:
+            params = {**self.options.additional_params, **params}
+
+        enable = self.options.enable if self.options.enable is not None else True
+        return {"enable": enable, "vendor": "generic", "params": params}
+
+
 class AnamAvatarOptions(BaseModel):
     model_config = ConfigDict(extra="forbid")
 

src/agora_agent/agentkit/vendors/llm.py

@@ -1,7 +1,10 @@
-from typing import Any, Dict, List, Optional
+from typing import Any, Dict, List, Optional, Union
 
 from pydantic import BaseModel, ConfigDict, Field, model_validator
 
+from ...agents.types.start_agents_request_properties_llm_greeting_configs import (
+    StartAgentsRequestPropertiesLlmGreetingConfigs,
+)
 from .base import BaseLLM
 
 LlmGreetingConfigs = Dict[str, Any]

src/agora_agent/agentkit/vendors/mllm.py

@@ -1,3 +1,4 @@
+import warnings
 from typing import Any, Dict, List, Optional
 
 from pydantic import BaseModel, ConfigDict, Field

src/agora_agent/agentkit/vendors/stt.py

@@ -89,6 +89,7 @@ class SpeechmaticsSTTOptions(BaseModel):
 
     api_key: str = Field(..., description="Speechmatics API key")
     language: str = Field(..., description="Language code (e.g., en, es, fr)")
+    interaction_language: Optional[InteractionLanguage] = Field(default=None, description="Agora interaction language for asr.language")
     model: Optional[str] = Field(default=None, description="Model name")
     uri: Optional[str] = Field(default=None, description="Speechmatics streaming WebSocket URL")
     additional_params: Optional[Dict[str, Any]] = Field(default=None)
@@ -124,6 +125,7 @@ class DeepgramSTTOptions(BaseModel):
     api_key: Optional[str] = Field(default=None, description="Deepgram API key")
     model: Optional[str] = Field(default=None, description="Model (e.g., nova-2, enhanced, base)")
     language: Optional[str] = Field(default=None, description="Language code (e.g., en-US)")
+    interaction_language: Optional[InteractionLanguage] = Field(default=None, description="Agora interaction language for asr.language")
     smart_format: Optional[bool] = Field(default=None, description="Enable smart formatting")
     punctuation: Optional[bool] = Field(default=None, description="Enable punctuation")
     additional_params: Optional[Dict[str, Any]] = Field(default=None)
@@ -353,6 +355,7 @@ class SarvamSTTOptions(BaseModel):
 
     api_key: str = Field(..., description="Sarvam API key")
     language: str = Field(..., description="Language code (e.g., en, hi, ta)")
+    interaction_language: Optional[InteractionLanguage] = Field(default=None, description="Agora interaction language for asr.language")
     model: Optional[str] = Field(default=None, description="Model name")
     additional_params: Optional[Dict[str, Any]] = Field(default=None)
 

src/agora_agent/agentkit/vendors/tts.py

@@ -139,6 +139,8 @@ def to_config(self) -> Dict[str, Any]:
         }
         if self.options.api_key is not None:
             params["api_key"] = self.options.api_key
+        if self.options.base_url is not None:
+            params["base_url"] = self.options.base_url
             params["base_url"] = self.options.base_url
             params["model"] = self.options.model
         elif self.options.model is not None:
@@ -254,6 +256,8 @@ def to_config(self) -> Dict[str, Any]:
             "voice": self.options.voice_id,
             "engine": self.options.engine,
         }
+        if self.options.engine is not None:
+            params["engine"] = self.options.engine
 
         result: Dict[str, Any] = {"vendor": "amazon", "params": params}
         if self.options.skip_patterns is not None:
@@ -392,6 +396,8 @@ def to_config(self) -> Dict[str, Any]:
             "reference_id": self.options.reference_id,
             "backend": self.options.backend,
         }
+        if self.options.backend is not None:
+            params["backend"] = self.options.backend
 
         result: Dict[str, Any] = {"vendor": "fishaudio", "params": params}
         if self.options.skip_patterns is not None:

src/agora_agent/core/client_wrapper.py

@@ -26,10 +26,10 @@ def __init__(
 
     def get_headers(self) -> typing.Dict[str, str]:
         headers: typing.Dict[str, str] = {
-            "User-Agent": "agora-agents/v2.1.1",
+            "User-Agent": "agora-agents/v2.1.2",
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "agora-agents",
-            "X-Fern-SDK-Version": "v2.1.1",
+            "X-Fern-SDK-Version": "v2.1.2",
             **(self.get_custom_headers() or {}),
         }
         headers["Authorization"] = httpx.BasicAuth(self._get_username(), self._get_password())._auth_header

src/agora_agent/types/asr.py

@@ -54,7 +54,6 @@ class Asr_Deepgram(UncheckedBaseModel):
     vendor: typing.Literal["deepgram"] = "deepgram"
     language: typing.Optional[AsrLanguage] = None
     params: DeepgramAsrParams
-    keyterm: typing.Optional[str] = None
 
     if IS_PYDANTIC_V2:
         model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2

src/agora_agent/types/deepgram_asr.py

@@ -16,10 +16,6 @@ class DeepgramAsr(UncheckedBaseModel):
 
     language: typing.Optional[AsrLanguage] = None
     params: DeepgramAsrParams
-    keyterm: typing.Optional[str] = pydantic.Field(default=None)
-    """
-    Boost specialized terms and brands for preset-backed Deepgram usage.
-    """
 
     if IS_PYDANTIC_V2:
         model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2

src/agora_agent/types/deepgram_asr_params.py

@@ -34,7 +34,7 @@ class DeepgramAsrParams(UncheckedBaseModel):
 
     keyterm: typing.Optional[str] = pydantic.Field(default=None)
     """
-    Boost specialized terms and brands
+    Boost specialized terms and brands for Deepgram.
     """
 
     if IS_PYDANTIC_V2: