pyaudioai package
Submodules
pyaudioai.OpenAiResponse module
- class pyaudioai.OpenAiResponse.OpenAiResponse(api_key, model='gpt-3.5-turbo', audio_model='whisper-1')[Quellcode]
Bases:
objectA class used to get a text or an audi response from OpenAI ChatGPT.
- api_key
key to authenticate through OpenAI API https://platform.openai.com/account/api-keys
- Type:
str
- model
select a ChatGPT model https://platform.openai.com/docs/guides/gpt (default gpt-3.5-turbo)
- Type:
str
- audio_model
select a speech to text model https://platform.openai.com/docs/guides/speech-to-text (default whisper-1)
- Type:
str
- get_audio_response(audio_file)[Quellcode]
Get an audio response of an audio file which contains a question. The function converts the text repsonse with TTS to an audio object and plays the audio.
- Parameter:
audio_file (str, required) – Path to an audio file which contains a questio
- get_text_response(audio_file)[Quellcode]
Get a text response of an audio file which contains a question.
- Parameter:
audio_file (str, required) – Path to an audio file which contains a question
- Rückgabe:
response from ChatGPT as text
- Rückgabetyp:
str
- transcribe(audio_file)[Quellcode]
Transcribe an audio file to text.
- Parameter:
audio_file (str, required) – Path to an audio file which contains a question
- Verursacht:
FileNotFoundError – If the audio file is not found
pyaudioai.RecordQuestion module
- class pyaudioai.RecordQuestion.RecordQuestion(recording_time, audio_file)[Quellcode]
Bases:
objectA class used to record an audio file with the computers microphone.
- recording_time
recording time in seconds
- Type:
int
- audio_file
Path to an audio file where the question is stored temporarily.
- Type:
str
- delete_file()[Quellcode]
Delete the temporary generated audio file.
- record()[Quellcode]
Record the audio file.