livekit-plugins-google 1.2.2__tar.gz → 1.2.4__tar.gz

{livekit_plugins_google-1.2.2 → livekit_plugins_google-1.2.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: livekit-plugins-google
-Version: 1.2.2
+Version: 1.2.4
 Summary: Agent Framework plugin for services from Google Cloud
 Project-URL: Documentation, https://docs.livekit.io
 Project-URL: Website, https://livekit.io/
@@ -22,7 +22,7 @@ Requires-Dist: google-auth<3,>=2
 Requires-Dist: google-cloud-speech<3,>=2
 Requires-Dist: google-cloud-texttospeech<3,>=2.27
 Requires-Dist: google-genai>=v1.23.0
-Requires-Dist: livekit-agents>=1.2.2
+Requires-Dist: livekit-agents>=1.2.4
 Description-Content-Type: text/markdown
 
 # Google AI plugin for LiveKit Agents

{livekit_plugins_google-1.2.2 → livekit_plugins_google-1.2.4}/livekit/plugins/google/beta/realtime/api_proto.py

@@ -9,6 +9,7 @@ LiveAPIModels = Literal[
     "gemini-2.0-flash-exp",
     # models supported on Gemini API
     "gemini-2.0-flash-live-001",
+    "gemini-live-2.5-flash-preview",
     "gemini-2.5-flash-preview-native-audio-dialog",
     "gemini-2.5-flash-exp-native-audio-thinking-dialog",
 ]

{livekit_plugins_google-1.2.2 → livekit_plugins_google-1.2.4}/livekit/plugins/google/beta/realtime/realtime_api.py

@@ -8,6 +8,7 @@ import time
 import weakref
 from collections.abc import Iterator
 from dataclasses import dataclass, field
+from typing import Literal
 
 from google import genai
 from google.genai import types
@@ -542,7 +543,12 @@ class RealtimeSession(llm.RealtimeSession):
         self.start_user_activity()
 
     def truncate(
-        self, *, message_id: str, audio_end_ms: int, audio_transcript: NotGivenOr[str] = NOT_GIVEN
+        self,
+        *,
+        message_id: str,
+        modalities: list[Literal["text", "audio"]],
+        audio_end_ms: int,
+        audio_transcript: NotGivenOr[str] = NOT_GIVEN,
     ) -> None:
         logger.warning("truncate is not supported by the Google Realtime API.")
         pass
@@ -786,10 +792,6 @@ class RealtimeSession(llm.RealtimeSession):
             logger.warning("starting new generation while another is active. Finalizing previous.")
             self._mark_current_generation_done()
 
-        # emit input_speech_started event before starting a new generation
-        # to interrupt the previous audio playout if any
-        self._handle_input_speech_started()
-
         response_id = utils.shortuuid("GR_")
         self._current_generation = _ResponseGeneration(
             message_ch=utils.aio.Chan[llm.MessageGeneration](),
@@ -803,11 +805,16 @@ class RealtimeSession(llm.RealtimeSession):
         if not self._realtime_model.capabilities.audio_output:
             self._current_generation.audio_ch.close()
 
+        msg_modalities = asyncio.Future[list[Literal["text", "audio"]]]()
+        msg_modalities.set_result(
+            ["audio", "text"] if self._realtime_model.capabilities.audio_output else ["text"]
+        )
         self._current_generation.message_ch.send_nowait(
             llm.MessageGeneration(
                 message_id=response_id,
                 text_stream=self._current_generation.text_ch,
                 audio_stream=self._current_generation.audio_ch,
+                modalities=msg_modalities,
             )
         )
 
@@ -821,6 +828,10 @@ class RealtimeSession(llm.RealtimeSession):
             generation_event.user_initiated = True
             self._pending_generation_fut.set_result(generation_event)
             self._pending_generation_fut = None
+        else:
+            # emit input_speech_started event before starting an agent initiated generation
+            # to interrupt the previous audio playout if any
+            self._handle_input_speech_started()
 
         self.emit("generation_created", generation_event)
 
@@ -936,9 +947,7 @@ class RealtimeSession(llm.RealtimeSession):
     def _handle_input_speech_stopped(self) -> None:
         self.emit(
             "input_speech_stopped",
-            llm.InputSpeechStoppedEvent(
-                user_transcription_enabled=self._realtime_model.capabilities.user_transcription
-            ),
+            llm.InputSpeechStoppedEvent(user_transcription_enabled=False),
         )
 
     def _handle_tool_calls(self, tool_call: types.LiveServerToolCall) -> None:

{livekit_plugins_google-1.2.2 → livekit_plugins_google-1.2.4}/livekit/plugins/google/models.py

@@ -15,81 +15,174 @@ SpeechModels = Literal[
 ]
 
 SpeechLanguages = Literal[
-    "en-US",
-    "ja-JP",
-    "en-IN",
-    "en-GB",
-    "hi-IN",
     "af-ZA",
-    "sq-AL",
     "am-ET",
+    "ar-AE",
+    "ar-BH",
+    "ar-DZ",
     "ar-EG",
-    "hy-AM",
+    "ar-IL",
+    "ar-IQ",
+    "ar-JO",
+    "ar-KW",
+    "ar-LB",
+    "ar-MA",
+    "ar-MR",
+    "ar-OM",
+    "ar-PS",
+    "ar-QA",
+    "ar-SA",
+    "ar-TN",
+    "ar-YE",
+    "as-IN",
     "ast-ES",
     "az-AZ",
-    "eu-ES",
     "be-BY",
-    "bs-BA",
     "bg-BG",
-    "my-MM",
+    "bn-BD",
+    "bn-IN",
+    "bs-BA",
     "ca-ES",
     "ceb-PH",
     "ckb-IQ",
-    "zh-Hans-CN",
-    "yue-Hant-HK",
-    "zh-TW",
-    "hr-HR",
+    "cmn-Hans-CN",
+    "cmn-Hant-TW",
     "cs-CZ",
+    "cy-GB",
     "da-DK",
-    "nl-NL",
+    "de-AT",
+    "de-CH",
+    "de-DE",
+    "el-GR",
     "en-AU",
+    "en-CA",
+    "en-GB",
+    "en-HK",
+    "en-IE",
+    "en-IN",
+    "en-NZ",
+    "en-PK",
+    "en-SG",
+    "en-US",
+    "es-419",
+    "es-AR",
+    "es-BO",
+    "es-CL",
+    "es-CO",
+    "es-CR",
+    "es-DO",
+    "es-EC",
+    "es-ES",
+    "es-GT",
+    "es-HN",
+    "es-MX",
+    "es-NI",
+    "es-PA",
+    "es-PE",
+    "es-PR",
+    "es-SV",
+    "es-US",
+    "es-UY",
+    "es-VE",
     "et-EE",
-    "fil-PH",
+    "eu-ES",
+    "fa-IR",
+    "ff-SN",
     "fi-FI",
+    "fil-PH",
+    "fr-BE",
     "fr-CA",
+    "fr-CH",
     "fr-FR",
+    "ga-IE",
     "gl-ES",
-    "ka-GE",
-    "de-DE",
-    "el-GR",
     "gu-IN",
     "ha-NG",
-    "iw-IL",
     "hi-IN",
+    "hr-HR",
     "hu-HU",
-    "is-IS",
+    "hy-AM",
     "id-ID",
+    "ig-NG",
+    "is-IS",
+    "it-CH",
     "it-IT",
+    "iw-IL",
     "ja-JP",
     "jv-ID",
-    "kea-CV",
+    "ka-GE",
     "kam-KE",
-    "kn-IN",
+    "kea-CV",
     "kk-KZ",
     "km-KH",
+    "kn-IN",
     "ko-KR",
     "ky-KG",
-    "lo-LA",
-    "lv-LV",
+    "lb-LU",
+    "lg-UG",
     "ln-CD",
+    "lo-LA",
     "lt-LT",
     "luo-KE",
-    "lb-LU",
+    "lv-LV",
+    "mi-NZ",
     "mk-MK",
+    "ml-IN",
+    "mn-MN",
+    "mr-IN",
+    "ms-MY",
+    "mt-MT",
+    "my-MM",
+    "ne-NP",
+    "nl-BE",
+    "nl-NL",
     "no-NO",
+    "nso-ZA",
+    "ny-MW",
+    "oc-FR",
+    "om-ET",
+    "or-IN",
+    "pa-Guru-IN",
     "pl-PL",
+    "ps-AF",
     "pt-BR",
     "pt-PT",
     "ro-RO",
     "ru-RU",
-    "es-CO",
-    "es-MX",
-    "es-US",
+    "rup-BG",
+    "rw-RW",
+    "sd-IN",
+    "si-LK",
+    "sk-SK",
+    "sl-SI",
+    "sn-ZW",
+    "so-SO",
+    "sq-AL",
+    "sr-RS",
+    "ss-Latn-ZA",
+    "st-ZA",
+    "su-ID",
+    "sv-SE",
+    "sw",
+    "sw-KE",
+    "ta-IN",
+    "te-IN",
+    "tg-TJ",
     "th-TH",
+    "tn-Latn-ZA",
     "tr-TR",
+    "ts-ZA",
     "uk-UA",
+    "umb-AO",
+    "ur-PK",
+    "uz-UZ",
+    "ve-ZA",
     "vi-VN",
-    "da-DK",
+    "wo-SN",
+    "xh-ZA",
+    "yo-NG",
+    "yue-Hant-HK",
+    "zu-ZA",
 ]
 
 Gender = Literal["male", "female", "neutral"]

{livekit_plugins_google-1.2.2 → livekit_plugins_google-1.2.4}/livekit/plugins/google/stt.py

@@ -66,6 +66,7 @@ class STTOptions:
     interim_results: bool
     punctuate: bool
     spoken_punctuation: bool
+    enable_word_time_offsets: bool
     model: SpeechModels | str
     sample_rate: int
     min_confidence_threshold: float
@@ -97,6 +98,7 @@ class STT(stt.STT):
         interim_results: bool = True,
         punctuate: bool = True,
         spoken_punctuation: bool = False,
+        enable_word_time_offsets: bool = True,
         model: SpeechModels | str = "latest_long",
         location: str = "global",
         sample_rate: int = 16000,
@@ -119,6 +121,7 @@ class STT(stt.STT):
             interim_results(bool): whether to return interim results (default: True)
             punctuate(bool): whether to punctuate the audio (default: True)
             spoken_punctuation(bool): whether to use spoken punctuation (default: False)
+            enable_word_time_offsets(bool): whether to enable word time offsets (default: True)
             model(SpeechModels): the model to use for recognition default: "latest_long"
             location(str): the location to use for recognition default: "global"
             sample_rate(int): the sample rate of the audio default: 16000
@@ -158,6 +161,7 @@ class STT(stt.STT):
             interim_results=interim_results,
             punctuate=punctuate,
             spoken_punctuation=spoken_punctuation,
+            enable_word_time_offsets=enable_word_time_offsets,
             model=model,
             sample_rate=sample_rate,
             min_confidence_threshold=min_confidence_threshold,
@@ -238,7 +242,7 @@ class STT(stt.STT):
             features=cloud_speech.RecognitionFeatures(
                 enable_automatic_punctuation=config.punctuate,
                 enable_spoken_punctuation=config.spoken_punctuation,
-                enable_word_time_offsets=True,
+                enable_word_time_offsets=config.enable_word_time_offsets,
             ),
             model=config.model,
             language_codes=config.languages,
@@ -490,7 +494,7 @@ class SpeechStream(stt.SpeechStream):
                             model=self._config.model,
                             features=cloud_speech.RecognitionFeatures(
                                 enable_automatic_punctuation=self._config.punctuate,
-                                enable_word_time_offsets=True,
+                                enable_word_time_offsets=self._config.enable_word_time_offsets,
                                 enable_spoken_punctuation=self._config.spoken_punctuation,
                             ),
                         ),

{livekit_plugins_google-1.2.2 → livekit_plugins_google-1.2.4}/livekit/plugins/google/version.py

@@ -12,4 +12,4 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__version__ = "1.2.2"
+__version__ = "1.2.4"

{livekit_plugins_google-1.2.2 → livekit_plugins_google-1.2.4}/pyproject.toml

@@ -27,7 +27,7 @@ dependencies = [
     "google-cloud-speech >= 2, < 3",
     "google-cloud-texttospeech >= 2.27, < 3",
     "google-genai >= v1.23.0",
-    "livekit-agents>=1.2.2",
+    "livekit-agents>=1.2.4",
 ]
 
 [project.urls]