moving Deepgram TTS base_url from beta to prod

This commit is contained in:
Kwindla Hultman Kramer
2024-05-28 15:59:26 -07:00
parent 650a2b4da4
commit 3685c19b2d
3 changed files with 105 additions and 3 deletions

View File

@@ -8,7 +8,7 @@ import aiohttp
from typing import AsyncGenerator
from pipecat.frames.frames import AudioRawFrame, Frame
from pipecat.frames.frames import AudioRawFrame, ErrorFrame, Frame
from pipecat.services.ai_services import TTSService
from loguru import logger
@@ -21,7 +21,7 @@ class DeepgramTTSService(TTSService):
*,
aiohttp_session: aiohttp.ClientSession,
api_key: str,
voice: str = "alpha-asteria-en-v2",
voice: str = "aura-helios-en",
**kwargs):
super().__init__(**kwargs)
@@ -31,11 +31,18 @@ class DeepgramTTSService(TTSService):
async def run_tts(self, text: str) -> AsyncGenerator[Frame, None]:
logger.info(f"Running Deepgram TTS for {text}")
base_url = "https://api.beta.deepgram.com/v1/speak"
base_url = "https://api.deepgram.com/v1/speak"
request_url = f"{base_url}?model={self._voice}&encoding=linear16&container=none&sample_rate=16000"
headers = {"authorization": f"token {self._api_key}"}
body = {"text": text}
async with self._aiohttp_session.post(request_url, headers=headers, json=body) as r:
if r.status != 200:
text = await r.text()
logger.error(f"Error getting audio (status: {r.status}, error: {text})")
yield ErrorFrame(f"Error getting audio (status: {r.status}, error: {text})")
return
async for data in r.content:
frame = AudioRawFrame(audio=data, sample_rate=16000, num_channels=1)
yield frame