[Python] Openai Issue, trying te generated Speech but always getting error

I am working on a app that can describe data into narration and then convert it into audio by using openai but always facing error while it creating the audio file, don't know where i am lacking

Narrater.py

import openai



def parse(narration):
output = []
lines = narration.split("/n")
for line in lines:
if line.startswith('Background: '):
background = line.replace("Background:","Background: ")
output.append({
"type":"image",
"description":background
})

elif line.startswith("Narration:"):
text = line.replace("Narration:","Narration:")
output.append({
"type":"text",
"content":text
})
return output


def create(data,output_path="output_audio.mp3"):
narration = "" # Initialize the narration variable as an empty string
for element in data:
if element["type"] != 'text':
continue
narration += element["content"] + "\n\n"
audio = openai.audio.speech.create(
model="tts-1",
input = narration,
voice="alloy"
)
audio.stream_to_file(output_path)


transcripter.py





# Read the source material from a file
with open("source_material.txt", "r") as f:
source_material = f.read()

# Create the chat completion
response = openai.chat.completions.create(
model="gpt-3.5-turbo",
messages=[
{
"role": "system",
"content": """You are a short Video Narratorthat reads the data and explains
it. You generate 30S TO 1 minutes of narration.
The short you create has a background that fades from image to image as the narration is going on.

Respond in the following manner, repeating until the end of the short:
Background: Description of background image based on the narration for AI Image Generation and also add the data
Narration: A few sentences of narration based on the data in detail

Background: Description of background image based on the narration for AI Image Generation with data and also add the data
Narration: A few sentences of narration based on the data in detail

Background: Description of background image based on the narration for AI Image Generation with data and also add the data
Narration: A few sentences of narration based on the data in detail

Background: Description of background image based on the narration for AI Image Generation with data and also add the data
Narration: A few sentences of narration based on the data in detail

Background: Description of background image based on the narration for AI Image Generation with data and also add the data
Narration: A few sentences of narration based on the data in detail


The short MUST be 6 sentences maximum.
"""
},
{
"role": "user",
"content": f"Create a short video narrator based on the following source material:\n\n{source_material}"
}
]
)

# Extract the generated content from the response
generated_content = response.choices[0].message.content

# Print the generated content
data = narrator.parse(generated_content)
print(data)
audio = narrator.create(data, "narration.mp3")


(myenv) PS D:\Python Data To Video\AppTest\Transcripter\myenv\DataTOVideo> python .\Transcripter.py [{'type': 'image', 'description': "Background: A dynamic and modern digital marketing office space with screens showing colorful graphs and charts related to advertising performance data.\nNarration: Analyzing the ad campaign performance data reveals a steady increase in impressions, clicks, and conversions over the course of five days. Costs also rise as the campaign expands, but so does revenue, indicating a positive return on investment.\n\nBackground: A sleek data analysis room with futuristic holographic displays showcasing various calculated metrics.\nNarration: By diving into the calculated metrics, we can see that the click-through rate remains relatively stable around 1.5%, while the cost per click fluctuates slightly. The conversion rate shows an upward trend, peaking on the third day, leading to a consistent return on ad spend (ROAS) above 2.00.\n\nBackground: An innovative marketing agency setting with screens displaying detailed performance breakdowns and key metrics.\nNarration: Through a closer examination of the data, it's evident that the ad campaign is performing well overall, with a healthy balance between cost-efficiency and conversion optimization. The trends indicate potential areas for further optimization to maximize results and drive even higher ROAS.\n\nBackground: A futuristic control center environment with real-time updates on ad campaign performance metrics.\nNarration: The ad campaign's success is reflected in the calculated metrics, showcasing a solid click-through rate alongside a cost per click that remains competitive. With conversion rates on the rise and a stable ROAS above 2.00, the data highlights a well-executed and profitable advertising strategy.\n\nBackground: A high-tech data visualization room with interactive screens illustrating the impact of various advertising strategies.\nNarration: Overall, the ad campaign's performance data and calculated metrics paint a picture of a well-managed and effective marketing initiative. The consistent growth in key metrics, paired with a positive return on ad spend, underscores the success of the campaign in driving both engagement and revenue for the business."}] Traceback (most recent call last): File "D:\Python Data To Video\AppTest\Transcripter\myenv\DataTOVideo\Transcripter.py", line 56, in audio = narrator.create(data, "narration.mp3") ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Python Data To Video\AppTest\Transcripter\myenv\DataTOVideo\narrator.py", line 42, in create audio = openai.audio.speech.create( ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Python Data To Video\AppTest\Transcripter\myenv\Lib\site-packages\openai\resources\audio\speech.py", line 96, in create return self._post( stream_cls=stream_cls)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Python Data To Video\AppTest\Transcripter\myenv\Lib\site-packages\openai_base_client.py", line 957, in request return self._request( ^^^^^^^^^^^^^^ File "D:\Python Data To Video\AppTest\Transcripter\myenv\Lib\site-packages\openai_base_client.py", line 1061, in _request raise self._make_status_error_from_response(err.response) from None openai.BadRequestError: Error code: 400 - {'error': {'message': "[{'type': 'string_too_short', 'loc': ('body', 'input'), 'msg': 'String should have at least 1 character', 'input': '', 'ctx': {'min_length': 1}}]", 'type': 'invalid_request_error', 'param': None, 'code': None}} (myenv) PS D:\Python Data To Video\AppTest\Transcripter\myenv\DataTOVideo>

I tried to downgrade the openai but it didn't work therefore i went to default

Continue reading...