Speech to Text Assembly AI

stt.py

# Assembly AI speech to text
def assemblyai_stt(audio_filename):
    with open(audio_filename , "rb") as f:
        response = requests.post(base_url + "/upload",
                                headers=headers,
                                data=f)

    upload_url = response.json()["upload_url"]
    data = {
        "audio_url": upload_url
    }
    url = base_url + "/transcript"
    response = requests.post(url, json=data, headers=headers)
    transcript_id = response.json()['id']
    polling_endpoint = f"https://api.assemblyai.com/v2/transcript/{transcript_id}"

    while True:
        transcription_result = requests.get(polling_endpoint, headers=headers).json()

        if transcription_result['status'] == 'completed':
            break

        elif transcription_result['status'] == 'error':
            raise RuntimeError(f"Transcription failed: {transcription_result['error']}")

        else:
            print("Processing...")
            time.sleep(3)
    print(transcription_result['text'])
    file = open('docs/transcription.txt', 'w')
    file.write(transcription_result['text'])
    file.close()
    return transcription_result['text']

base_url = "https://api.assemblyai.com/v2"

headers = {
"authorization": api_token,
"content-type": "application/json"
}