marcocosta10000
25288d2c0f
Add a voice message handler that downloads OGG audio, converts it to WAV via pydub/ffmpeg, and transcribes it with Google Speech Recognition (pt-BR) before feeding the text into the normal message pipeline. Also extract shared text processing into process_text_message, guard against updates without a text attribute, switch the default AI provider to openrouter with deepseek-v4-flash, and document the ffmpeg system requirement in DEPLOY.md.
43 lines
1.5 KiB
Python
43 lines
1.5 KiB
Python
from __future__ import annotations
|
|
|
|
import os
|
|
from io import BytesIO
|
|
|
|
from speech_recognition.audio import AudioData
|
|
from speech_recognition.exceptions import SetupError
|
|
|
|
|
|
def recognize_whisper_api(
|
|
recognizer,
|
|
audio_data: "AudioData",
|
|
*,
|
|
model: str = "whisper-1",
|
|
api_key: str | None = None,
|
|
):
|
|
"""
|
|
Performs speech recognition on ``audio_data`` (an ``AudioData`` instance), using the OpenAI Whisper API.
|
|
|
|
This function requires an OpenAI account; visit https://platform.openai.com/signup, then generate API Key in `User settings <https://platform.openai.com/account/api-keys>`__.
|
|
|
|
Detail: https://platform.openai.com/docs/guides/speech-to-text
|
|
|
|
Raises a ``speech_recognition.exceptions.SetupError`` exception if there are any issues with the openai installation, or the environment variable is missing.
|
|
"""
|
|
if not isinstance(audio_data, AudioData):
|
|
raise ValueError("``audio_data`` must be an ``AudioData`` instance")
|
|
if api_key is None and os.environ.get("OPENAI_API_KEY") is None:
|
|
raise SetupError("Set environment variable ``OPENAI_API_KEY``")
|
|
|
|
try:
|
|
import openai
|
|
except ImportError:
|
|
raise SetupError(
|
|
"missing openai module: ensure that openai is set up correctly."
|
|
)
|
|
|
|
wav_data = BytesIO(audio_data.get_wav_data())
|
|
wav_data.name = "SpeechRecognition_audio.wav"
|
|
|
|
transcript = openai.Audio.transcribe(model, wav_data, api_key=api_key)
|
|
return transcript["text"]
|