Spaces:
Runtime error
Runtime error
File size: 2,898 Bytes
ea22b9d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 |
"""ElevenLabs speech module"""
import os
import requests
from playsound import playsound
from autogpt.config import Config
from autogpt.speech.base import VoiceBase
PLACEHOLDERS = {"your-voice-id"}
class ElevenLabsSpeech(VoiceBase):
"""ElevenLabs speech class"""
def _setup(self) -> None:
"""Set up the voices, API key, etc.
Returns:
None: None
"""
cfg = Config()
default_voices = ["ErXwobaYiN019PkySvjV", "EXAVITQu4vr4xnSDxMaL"]
voice_options = {
"Rachel": "21m00Tcm4TlvDq8ikWAM",
"Domi": "AZnzlk1XvdvUeBnXmlld",
"Bella": "EXAVITQu4vr4xnSDxMaL",
"Antoni": "ErXwobaYiN019PkySvjV",
"Elli": "MF3mGyEYCl7XYWbV9V6O",
"Josh": "TxGEqnHWrfWFTfGW9XjX",
"Arnold": "VR6AewLTigWG4xSOukaG",
"Adam": "pNInz6obpgDQGcFmaJgB",
"Sam": "yoZ06aMxZJJ28mfd3POQ",
}
self._headers = {
"Content-Type": "application/json",
"xi-api-key": cfg.elevenlabs_api_key,
}
self._voices = default_voices.copy()
if cfg.elevenlabs_voice_1_id in voice_options:
cfg.elevenlabs_voice_1_id = voice_options[cfg.elevenlabs_voice_1_id]
if cfg.elevenlabs_voice_2_id in voice_options:
cfg.elevenlabs_voice_2_id = voice_options[cfg.elevenlabs_voice_2_id]
self._use_custom_voice(cfg.elevenlabs_voice_1_id, 0)
self._use_custom_voice(cfg.elevenlabs_voice_2_id, 1)
def _use_custom_voice(self, voice, voice_index) -> None:
"""Use a custom voice if provided and not a placeholder
Args:
voice (str): The voice ID
voice_index (int): The voice index
Returns:
None: None
"""
# Placeholder values that should be treated as empty
if voice and voice not in PLACEHOLDERS:
self._voices[voice_index] = voice
def _speech(self, text: str, voice_index: int = 0) -> bool:
"""Speak text using elevenlabs.io's API
Args:
text (str): The text to speak
voice_index (int, optional): The voice to use. Defaults to 0.
Returns:
bool: True if the request was successful, False otherwise
"""
tts_url = (
f"https://api.elevenlabs.io/v1/text-to-speech/{self._voices[voice_index]}"
)
response = requests.post(tts_url, headers=self._headers, json={"text": text})
if response.status_code == 200:
with open("speech.mpeg", "wb") as f:
f.write(response.content)
playsound("speech.mpeg", True)
os.remove("speech.mpeg")
return True
else:
print("Request failed with status code:", response.status_code)
print("Response content:", response.content)
return False
|