added TTS agent for voice messages

pyproject.toml

@@ -12,6 +12,7 @@ dependencies = [
     "dishka>=1.6.0",
     "google-genai>=1.23.0",
     "pydantic-settings>=2.10.1",
+    "pydub>=0.25.1",
     "rich>=14.0.0",
 ]
 

src/bot/modules/solaris/agents/tts.py

@@ -0,0 +1,32 @@
+import io
+import json
+from google import genai
+from google.genai import types
+from pydub import AudioSegment
+from ..content_configs import TTS_CONTENT_CONFIG
+
+class TTSAgent:
+    def __init__(self, api_key: str) -> None:
+        # код повторяется некрасиво
+        self.client = genai.Client(api_key=api_key).aio
+    async def generate(self, text: str):
+        response = await self.client.models.generate_content(
+            model="gemini-2.5-flash-preview-tts",
+            contents=text,
+            config=TTS_CONTENT_CONFIG
+        )
+        data = response.candidates[0].content.parts[0].inline_data.data
+        pcm_io = io.BytesIO(data)
+        audio = AudioSegment(
+            pcm_io.read(),
+            sample_width=2,
+            frame_rate=24000,
+            channels=1
+        )
+
+        # Экспортируем как .ogg с кодеком opus
+        ogg_io = io.BytesIO()
+        audio.export(ogg_io, format="ogg", codec="libopus")
+        ogg_bytes = ogg_io.getvalue()
+        return ogg_bytes
+

src/bot/modules/solaris/content_configs.py

@@ -2,7 +2,7 @@
 from google.genai import types 
 from .structures import OutputMessage
 
-CONTENT_CONFIG = types.GenerateContentConfig(
+MAIN_CONTENT_CONFIG = types.GenerateContentConfig(
     system_instruction="meow meow meow",  # надо где-то промпт хранить, в бд наверное хезе
     thinking_config=types.ThinkingConfig(thinking_budget=0),
     response_mime_type="application/json",
@@ -15,3 +15,21 @@ CONTENT_CONFIG = types.GenerateContentConfig(
         for category in types.HarmBlockThreshold
     ]
 )
+
+TTS_CONTENT_CONFIG = types.GenerateContentConfig(
+    response_modalities=["AUDIO"],
+    speech_config=types.SpeechConfig(
+        voice_config=types.VoiceConfig(
+            prebuilt_voice_config=types.PrebuiltVoiceConfig(
+                voice_name='Kore',
+            )
+        )
+    ),
+    safety_settings=[
+        types.SafetySetting(
+            category=category,
+            threshold=types.HarmBlockThreshold.OFF
+        )
+        for category in types.HarmBlockThreshold
+    ]
+)

uv.lock

@@ -548,6 +548,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/58/f0/427018098906416f580e3cf1366d3b1abfb408a0652e9f31600c24a1903c/pydantic_settings-2.10.1-py3-none-any.whl", hash = "sha256:a60952460b99cf661dc25c29c0ef171721f98bfcb52ef8d9ea4c943d7c8cc796", size = 45235, upload-time = "2025-06-24T13:26:45.485Z" },
 ]
 
+[[package]]
+name = "pydub"
+version = "0.25.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/fe/9a/e6bca0eed82db26562c73b5076539a4a08d3cffd19c3cc5913a3e61145fd/pydub-0.25.1.tar.gz", hash = "sha256:980a33ce9949cab2a569606b65674d748ecbca4f0796887fd6f46173a7b0d30f", size = 38326, upload-time = "2021-03-10T02:09:54.659Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/a6/53/d78dc063216e62fc55f6b2eebb447f6a4b0a59f55c8406376f76bf959b08/pydub-0.25.1-py2.py3-none-any.whl", hash = "sha256:65617e33033874b59d87db603aa1ed450633288aefead953b30bded59cb599a6", size = 32327, upload-time = "2021-03-10T02:09:53.503Z" },
+]
+
 [[package]]
 name = "pygments"
 version = "2.19.2"
@@ -654,6 +663,7 @@ dependencies = [
     { name = "dishka" },
     { name = "google-genai" },
     { name = "pydantic-settings" },
+    { name = "pydub" },
     { name = "rich" },
 ]
 
@@ -664,6 +674,7 @@ requires-dist = [
     { name = "dishka", specifier = ">=1.6.0" },
     { name = "google-genai", specifier = ">=1.23.0" },
     { name = "pydantic-settings", specifier = ">=2.10.1" },
+    { name = "pydub", specifier = ">=0.25.1" },
     { name = "rich", specifier = ">=14.0.0" },
 ]