Add string type support to model parameter (#1657)

Author: jayeshp19

.changeset/happy-nails-shout.md

@@ -0,0 +1,5 @@
+---
+"livekit-plugins-deepgram": patch
+---
+
+add `nova-3-medical` to stt models

.changeset/slow-mayflies-count.md

@@ -0,0 +1,9 @@
+---
+"livekit-plugins-neuphonic": patch
+"livekit-plugins-cartesia": patch
+"livekit-plugins-deepgram": patch
+"livekit-plugins-openai": patch
+"livekit-plugins-rime": patch
+---
+
+Add string type support to model parameter

livekit-plugins/livekit-plugins-cartesia/livekit/plugins/cartesia/tts.py

@@ -156,7 +156,7 @@ def prewarm(self) -> None:
     def update_options(
         self,
         *,
-        model: TTSModels | None = None,
+        model: TTSModels | str | None = None,
         language: str | None = None,
         voice: str | list[float] | None = None,
         speed: TTSVoiceSpeed | float | None = None,

livekit-plugins/livekit-plugins-clova/livekit/plugins/clova/stt.py

@@ -43,7 +43,7 @@ class STT(stt.STT):
     def __init__(
         self,
         *,
-        language: ClovaSttLanguages = "en-US",
+        language: ClovaSttLanguages | str = "en-US",
         secret: Optional[str] = None,
         invoke_url: Optional[str] = None,
         http_session: Optional[aiohttp.ClientSession] = None,

livekit-plugins/livekit-plugins-deepgram/livekit/plugins/deepgram/models.py

@@ -16,6 +16,7 @@
     "nova-2-automotive",
     "nova-3",
     "nova-3-general",
+    "nova-3-medical",
     "enhanced-general",
     "enhanced-meeting",
     "enhanced-phonecall",

livekit-plugins/livekit-plugins-deepgram/livekit/plugins/deepgram/stt.py

@@ -96,7 +96,7 @@ class STTOptions:
     detect_language: bool
     interim_results: bool
     punctuate: bool
-    model: DeepgramModels
+    model: DeepgramModels | str
     smart_format: bool
     no_delay: bool
     endpointing_ms: int
@@ -113,8 +113,8 @@ class STT(stt.STT):
     def __init__(
         self,
         *,
-        model: DeepgramModels = "nova-2-general",
-        language: DeepgramLanguages = "en-US",
+        model: DeepgramModels | str = "nova-2-general",
+        language: DeepgramLanguages | str = "en-US",
         detect_language: bool = False,
         interim_results: bool = True,
         punctuate: bool = True,
@@ -278,8 +278,8 @@ def stream(
     def update_options(
         self,
         *,
-        language: DeepgramLanguages | None = None,
-        model: DeepgramModels | None = None,
+        language: DeepgramLanguages | str | None = None,
+        model: DeepgramModels | str | None = None,
         interim_results: bool | None = None,
         punctuate: bool | None = None,
         smart_format: bool | None = None,
@@ -388,8 +388,8 @@ def __init__(
     def update_options(
         self,
         *,
-        language: DeepgramLanguages | None = None,
-        model: DeepgramModels | None = None,
+        language: DeepgramLanguages | str | None = None,
+        model: DeepgramModels | str | None = None,
         interim_results: bool | None = None,
         punctuate: bool | None = None,
         smart_format: bool | None = None,
@@ -739,8 +739,8 @@ def _to_deepgram_url(opts: dict, base_url: str, *, websocket: bool) -> str:
 
 
 def _validate_model(
-    model: DeepgramModels, language: DeepgramLanguages | str | None
-) -> DeepgramModels:
+    model: DeepgramModels | str, language: DeepgramLanguages | str | None
+) -> DeepgramModels | str:
     en_only_models = {
         "nova-2-meeting",
         "nova-2-phonecall",

livekit-plugins/livekit-plugins-openai/livekit/plugins/openai/stt.py

@@ -92,7 +92,7 @@ def __init__(
     def update_options(
         self,
         *,
-        model: WhisperModels | GroqAudioModels | None = None,
+        model: WhisperModels | GroqAudioModels | str | None = None,
         language: str | None = None,
         prompt: str | None = None,
     ) -> None:

livekit-plugins/livekit-plugins-openai/livekit/plugins/openai/tts.py

@@ -93,7 +93,11 @@ def __init__(
         )
 
     def update_options(
-        self, *, model: TTSModels | None, voice: TTSVoices | None, speed: float | None
+        self,
+        *,
+        model: TTSModels | str | None,
+        voice: TTSVoices | str | None,
+        speed: float | None,
     ) -> None:
         self._opts.model = model or self._opts.model
         self._opts.voice = voice or self._opts.voice
@@ -102,8 +106,8 @@ def update_options(
     @staticmethod
     def create_azure_client(
         *,
-        model: TTSModels = "tts-1",
-        voice: TTSVoices = "alloy",
+        model: TTSModels | str = "tts-1",
+        voice: TTSVoices | str = "alloy",
         speed: float = 1.0,
         azure_endpoint: str | None = None,
         azure_deployment: str | None = None,

livekit-plugins/livekit-plugins-rime/livekit/plugins/rime/tts.py

@@ -114,7 +114,7 @@ def synthesize(
     def update_options(
         self,
         *,
-        model: TTSModels | None,
+        model: TTSModels | str | None,
         speaker: str | None,
     ) -> None:
         self._opts.model = model or self._opts.model