update deepgram tts to new service structure
This commit is contained in:
36
src/dailyai/services/deepgram_ai_service.py
Normal file
36
src/dailyai/services/deepgram_ai_service.py
Normal file
@@ -0,0 +1,36 @@
|
||||
import os
|
||||
import aiohttp
|
||||
import requests
|
||||
|
||||
from dailyai.services.ai_services import TTSService
|
||||
|
||||
|
||||
class DeepgramAIService(TTSService):
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
aiohttp_session: aiohttp.ClientSession,
|
||||
api_key,
|
||||
voice,
|
||||
sample_rate=16000
|
||||
):
|
||||
super().__init__()
|
||||
|
||||
self._api_key = api_key
|
||||
self._voice = voice
|
||||
self._sample_rate = sample_rate
|
||||
self._aiohttp_session = aiohttp_session
|
||||
|
||||
async def run_tts(self, sentence):
|
||||
self.logger.info(f"Running deepgram tts for {sentence}")
|
||||
base_url = "https://api.beta.deepgram.com/v1/speak"
|
||||
request_url = f"{base_url}?model={self._voice}&encoding=linear16&container=none&sample_rate={self._sample_rate}"
|
||||
headers = {"authorization": f"token {self._api_key}", "Content-Type": "application/json"}
|
||||
data = {"text": sentence}
|
||||
|
||||
async with self._aiohttp_session.post(
|
||||
request_url, headers=headers, json=data
|
||||
) as r:
|
||||
async for chunk in r.content:
|
||||
if chunk:
|
||||
yield chunk
|
||||
@@ -1,29 +0,0 @@
|
||||
import os
|
||||
import requests
|
||||
|
||||
from services.ai_service import AIService
|
||||
from PIL import Image
|
||||
|
||||
|
||||
class DeepgramAIService(AIService):
|
||||
def __init__(self, **kwargs):
|
||||
super().__init__(**kwargs)
|
||||
|
||||
self.api_key = os.getenv("DEEPGRAM_API_KEY")
|
||||
|
||||
def get_mic_sample_rate(self):
|
||||
return 24000
|
||||
|
||||
def run_tts(self, sentence):
|
||||
self.logger.info(f"Running deepgram tts for {sentence}")
|
||||
base_url = "https://api.beta.deepgram.com/v1/speak"
|
||||
# move this to an environment variable
|
||||
voice = os.getenv("DEEPGRAM_VOICE") or "alpha-apollo-en-v1"
|
||||
request_url = f"{base_url}?model={voice}&encoding=linear16&container=none"
|
||||
headers = {"authorization": f"token {self.api_key}"}
|
||||
|
||||
r = requests.post(request_url, headers=headers, data=sentence)
|
||||
self.logger.info(
|
||||
f"audio fetch status code: {r.status_code}, content length: {len(r.content)}"
|
||||
)
|
||||
yield r.content
|
||||
Reference in New Issue
Block a user