400 Bad Request and Invalid type for instructions

[stanstrup]

I don't understand enough to be helpful about what the problem is but this is what I get when I try to convert an epub with openAI.

D:\Downloads>docker run -i -t --rm -v D:/Downloads/:/app -e OPENAI_API_KEY=NOOOOO ghcr.io/p0n1/epub_to_audiobook "my.epub" audiobook_output --tts openai
Starting entrypoint script...
Executing default command: python3 /app_src/main.py richter.epub audiobook_output --tts openai
/usr/local/lib/python3.11/site-packages/ebooklib/epub.py:1423: FutureWarning: This search incorrectly ignores the root element, and will be fixed in a future version.  If you rely on the current behaviour, change it to './/xmlns:rootfile[@media-type]'
  for root_file in tree.findall('//xmlns:rootfile[@media-type]', namespaces={'xmlns': NAMESPACES['CONTAINERNS']}):
2025-04-26 19:18:55,336 - audiobook_generator.py:105 - run - INFO - Chapters count: 1.
2025-04-26 19:18:55,337 - audiobook_generator.py:123 - run - INFO - Converting chapters from 1 to 1.
2025-04-26 19:18:55,337 - audiobook_generator.py:131 - run - INFO - ✨ Total characters in selected book chapters: 18437 ✨
Estimate book voiceover would cost you roughly: $0.06

Do you want to continue? (y/n)
y
2025-04-26 19:19:14,976 - [Worker-7] - audiobook_generator.py:60 - process_chapter - INFO - Processing chapter 1: NINA_LVOVNA
2025-04-26 19:19:15,214 - [Worker-7] - openai_tts_provider.py:70 - text_to_speech - INFO - Processing chapter-1_NINA_LVOVNA_chunk_1_of_11, length=1670
2025-04-26 19:19:15,936 - [Worker-7] - _client.py:1038 - _send_single_request - INFO - HTTP Request: POST https://api.openai.com/v1/audio/speech "HTTP/1.1 400 Bad Request"
2025-04-26 19:19:15,941 - [Worker-7] - audiobook_generator.py:87 - process_chapter - ERROR - Error processing chapter 1, error: Error code: 400 - {'error': {'message': "Invalid type for 'instructions': expected a string, but got null instead.", 'type': 'invalid_request_error', 'param': 'instructions', 'code': 'invalid_type'}}
Traceback (most recent call last):
  File "/app_src/audiobook_generator/core/audiobook_generator.py", line 81, in process_chapter
    tts_provider.text_to_speech(text, output_file, audio_tags)
  File "/app_src/audiobook_generator/tts_providers/openai_tts_provider.py", line 78, in text_to_speech
    response = self.client.audio.speech.create(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/resources/audio/speech.py", line 100, in create
    return self._post(
           ^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/_base_client.py", line 1242, in post
    return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/_base_client.py", line 919, in request
    return self._request(
           ^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/_base_client.py", line 1023, in _request
    raise self._make_status_error_from_response(err.response) from None
openai.BadRequestError: Error code: 400 - {'error': {'message': "Invalid type for 'instructions': expected a string, but got null instead.", 'type': 'invalid_request_error', 'param': 'instructions', 'code': 'invalid_type'}}
2025-04-26 19:19:15,966 - audiobook_generator.py:171 - run - WARNING - The following chapters failed to convert:
2025-04-26 19:19:15,967 - audiobook_generator.py:173 - run - WARNING -   - Chapter 1: NINA_LVOVNA
2025-04-26 19:19:15,967 - audiobook_generator.py:174 - run - INFO - Conversion completed with 1 failed chapters.

[p0n1]

Thanks for reporting. Will a default empty string for instructions flag help? Like docker run -i -t --rm -v D:/Downloads/:/app -e OPENAI_API_KEY=NOOOOO ghcr.io/p0n1/epub_to_audiobook "my.epub" audiobook_output --tts openai --instructions "".

Looks like a code issue related to bellow:

epub_to_audiobook/audiobook_generator/tts_providers/openai_tts_provider.py

Line 46 in 1ef840b

config.instructions = config.instructions or None

[stanstrup]

Unfortunately no.

docker run -i -t --rm -v D:/Downloads/:/app -e OPENAI_API_KEY=NOOOO ghcr.io/p0n1/epub_to_audiobook "my.epub" audiobook_output --tts openai --instructions ""

Starting entrypoint script...
Executing default command: python3 /app_src/main.py my.epub audiobook_output --tts openai --instructions
/usr/local/lib/python3.11/site-packages/ebooklib/epub.py:1423: FutureWarning: This search incorrectly ignores the root element, and will be fixed in a future version.  If you rely on the current behaviour, change it to './/xmlns:rootfile[@media-type]'
  for root_file in tree.findall('//xmlns:rootfile[@media-type]', namespaces={'xmlns': NAMESPACES['CONTAINERNS']}):
2025-04-28 07:49:45,215 - audiobook_generator.py:105 - run - INFO - Chapters count: 1.
2025-04-28 07:49:45,215 - audiobook_generator.py:123 - run - INFO - Converting chapters from 1 to 1.
2025-04-28 07:49:45,215 - audiobook_generator.py:131 - run - INFO - ✨ Total characters in selected book chapters: 18437 ✨
Estimate book voiceover would cost you roughly: $0.06

Do you want to continue? (y/n)
y
2025-04-28 07:49:47,711 - [Worker-7] - audiobook_generator.py:60 - process_chapter - INFO - Processing chapter 1: NINA_LVOVNA
2025-04-28 07:49:47,959 - [Worker-7] - openai_tts_provider.py:70 - text_to_speech - INFO - Processing chapter-1_NINA_LVOVNA_chunk_1_of_11, length=1670
2025-04-28 07:49:49,113 - [Worker-7] - _client.py:1038 - _send_single_request - INFO - HTTP Request: POST https://api.openai.com/v1/audio/speech "HTTP/1.1 400 Bad Request"
2025-04-28 07:49:49,118 - [Worker-7] - audiobook_generator.py:87 - process_chapter - ERROR - Error processing chapter 1, error: Error code: 400 - {'error': {'message': "Invalid type for 'instructions': expected a string, but got null instead.", 'type': 'invalid_request_error', 'param': 'instructions', 'code': 'invalid_type'}}
Traceback (most recent call last):
  File "/app_src/audiobook_generator/core/audiobook_generator.py", line 81, in process_chapter
    tts_provider.text_to_speech(text, output_file, audio_tags)
  File "/app_src/audiobook_generator/tts_providers/openai_tts_provider.py", line 78, in text_to_speech
    response = self.client.audio.speech.create(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/resources/audio/speech.py", line 100, in create
    return self._post(
           ^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/_base_client.py", line 1242, in post
    return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/_base_client.py", line 919, in request
    return self._request(
           ^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/_base_client.py", line 1023, in _request
    raise self._make_status_error_from_response(err.response) from None
openai.BadRequestError: Error code: 400 - {'error': {'message': "Invalid type for 'instructions': expected a string, but got null instead.", 'type': 'invalid_request_error', 'param': 'instructions', 'code': 'invalid_type'}}
2025-04-28 07:49:49,155 - audiobook_generator.py:171 - run - WARNING - The following chapters failed to convert:
2025-04-28 07:49:49,155 - audiobook_generator.py:173 - run - WARNING -   - Chapter 1: some chap
2025-04-28 07:49:49,155 - audiobook_generator.py:174 - run - INFO - Conversion completed with 1 failed chapters.

[p0n1]

That's strange. I tested on my end and it worked. I see you're using the official OpenAI URL and docker. So everything should be the same. Would my mind try the following commands again?

docker run -i -t --rm -v D:/Downloads/:/app -e OPENAI_API_KEY=NOOOO ghcr.io/p0n1/epub_to_audiobook "my.epub" audiobook_output --tts openai --instructions "normal voice" --log DEBUG

And

docker run -i -t --rm -v D:/Downloads/:/app -e OPENAI_API_KEY=NOOOO ghcr.io/p0n1/epub_to_audiobook "my.epub" audiobook_output --tts openai --log DEBUG

And you can find and post the similar log like bellow:

2025-04-28 14:36:30,526 - [Worker-9] - _base_client.py:453 - _build_request - DEBUG - Request options: {'method': 'post', 'url': '/audio/speech', 'headers': {'Accept': 'application/octet-stream'}, 'files': None, 'json_data': {'input': 'Book content', 'model': 'gpt-4o-mini-tts', 'voice': 'ash', 'instructions': None, 'response_format': 'mp3', 'speed': 1.0}}

I think the OpenAI sdk supports assign None to instructions var.

epub_to_audiobook/audiobook_generator/tts_providers/openai_tts_provider.py

Line 46 in 1ef840b

config.instructions = config.instructions or None

https://github.com/openai/openai-python/blob/8e1a1cd60d990361b934f922fd7d176f2ae0a63c/src/openai/resources/audio/speech.py#L101-L108

[stanstrup]

With instructions (works!)

docker run -i -t --rm -v D:/Downloads/:/app -e OPENAI_API_KEY=NOOOO ghcr.io/p0n1/epub_to_audiobook "my.epub" audiobook_output --tts openai --instructions "normal voice" --log DEBUG
Starting entrypoint script...
Executing default command: python3 /app_src/main.py my.epub audiobook_output --tts openai --instructions normal voice --log DEBUG
/usr/local/lib/python3.11/site-packages/ebooklib/epub.py:1423: FutureWarning: This search incorrectly ignores the root element, and will be fixed in a future version.  If you rely on the current behaviour, change it to './/xmlns:rootfile[@media-type]'
  for root_file in tree.findall('//xmlns:rootfile[@media-type]', namespaces={'xmlns': NAMESPACES['CONTAINERNS']}):
2025-04-28 15:14:22,849 - _config.py:82 - load_ssl_context - DEBUG - load_ssl_context verify=True cert=None trust_env=True http2=False
2025-04-28 15:14:22,869 - _config.py:148 - load_ssl_context_verify - DEBUG - load_verify_locations cafile='/usr/local/lib/python3.11/site-packages/certifi/cacert.pem'
2025-04-28 15:14:23,007 - epub_book_parser.py:49 - get_chapters - DEBUG - Raw text: <

>
2025-04-28 15:14:23,007 - epub_book_parser.py:61 - get_chapters - DEBUG - Cleaned text step 1: <>
2025-04-28 15:14:23,007 - epub_book_parser.py:63 - get_chapters - DEBUG - Cleaned text step 2: <>
2025-04-28 15:14:23,007 - epub_book_parser.py:78 - get_chapters - DEBUG - Cleaned text step 5: <>
2025-04-28 15:14:23,007 - epub_book_parser.py:103 - get_chapters - DEBUG - Raw title: <>
2025-04-28 15:14:23,008 - epub_book_parser.py:105 - get_chapters - DEBUG - Sanitized title: <>
2025-04-28 15:14:23,012 - epub_book_parser.py:49 - get_chapters - DEBUG - Raw text: <


[TEXT]



>
2025-04-28 15:14:23,013 - epub_book_parser.py:61 - get_chapters - DEBUG - Cleaned text step 1: <[TEXT]>
2025-04-28 15:14:23,017 - epub_book_parser.py:63 - get_chapters - DEBUG - Cleaned text step 2: <TEXT>
2025-04-28 15:14:23,017 - epub_book_parser.py:78 - get_chapters - DEBUG - Cleaned text step 5: <TEXT>
2025-04-28 15:14:23,019 - epub_book_parser.py:103 - get_chapters - DEBUG - Raw title: <TEXT>
2025-04-28 15:14:23,019 - epub_book_parser.py:105 - get_chapters - DEBUG - Sanitized title: <TEXT>
2025-04-28 15:14:23,019 - audiobook_generator.py:105 - run - INFO - Chapters count: 1.
2025-04-28 15:14:23,019 - audiobook_generator.py:123 - run - INFO - Converting chapters from 1 to 1.
2025-04-28 15:14:23,019 - audiobook_generator.py:131 - run - INFO - ✨ Total characters in selected book chapters: 18437 ✨
Estimate book voiceover would cost you roughly: $0.06

Do you want to continue? (y/n)
y
2025-04-28 15:14:25,854 - [Worker-7] - audiobook_generator.py:60 - process_chapter - INFO - Processing chapter 1: chap1
2025-04-28 15:14:25,856 - [Worker-7] - _config.py:82 - load_ssl_context - DEBUG - load_ssl_context verify=True cert=None trust_env=True http2=False
2025-04-28 15:14:25,858 - [Worker-7] - _config.py:148 - load_ssl_context_verify - DEBUG - load_verify_locations cafile='/usr/local/lib/python3.11/site-packages/certifi/cacert.pem'
2025-04-28 15:14:26,085 - [Worker-7] - openai_tts_provider.py:70 - text_to_speech - INFO - Processing chapter-chap1_chunk_1_of_11, length=1670
2025-04-28 15:14:26,085 - [Worker-7] - openai_tts_provider.py:73 - text_to_speech - DEBUG - Processing chapter-chap1_chunk_1_of_11, length=1670, text=[TEXT]
2025-04-28 15:14:26,088 - [Worker-7] - _base_client.py:453 - _build_request - DEBUG - Request options: {'method': 'post', 'url': '/audio/speech', 'headers': {'Accept': 'application/octet-stream'}, 'files': None, 'json_data': {'input': '[TEXT]', 'model': 'gpt-4o-mini-tts', 'voice': 'alloy', 'instructions': 'normal voice', 'response_format': 'mp3', 'speed': 1.0}}
2025-04-28 15:14:26,113 - [Worker-7] - _base_client.py:952 - _request - DEBUG - Sending HTTP Request: POST https://api.openai.com/v1/audio/speech
2025-04-28 15:14:26,114 - [Worker-7] - _trace.py:47 - trace - DEBUG - connect_tcp.started host='api.openai.com' port=443 local_address=None timeout=5.0 socket_options=None
2025-04-28 15:14:26,202 - [Worker-7] - _trace.py:47 - trace - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x7fef3c344ad0>
2025-04-28 15:14:26,202 - [Worker-7] - _trace.py:47 - trace - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x7fef3c5a3b60> server_hostname='api.openai.com' timeout=5.0
2025-04-28 15:14:26,220 - [Worker-7] - _trace.py:47 - trace - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x7fef3c344d50>
2025-04-28 15:14:26,221 - [Worker-7] - _trace.py:47 - trace - DEBUG - send_request_headers.started request=<Request [b'POST']>
2025-04-28 15:14:26,222 - [Worker-7] - _trace.py:47 - trace - DEBUG - send_request_headers.complete
2025-04-28 15:14:26,222 - [Worker-7] - _trace.py:47 - trace - DEBUG - send_request_body.started request=<Request [b'POST']>
2025-04-28 15:14:26,222 - [Worker-7] - _trace.py:47 - trace - DEBUG - send_request_body.complete
2025-04-28 15:14:26,223 - [Worker-7] - _trace.py:47 - trace - DEBUG - receive_response_headers.started request=<Request [b'POST']>
2025-04-28 15:14:28,163 - [Worker-7] - _trace.py:47 - trace - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Mon, 28 Apr 2025 15:14:28 GMT'), (b'Content-Type', b'audio/mpeg'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'access-control-expose-headers', b'X-Request-ID'), (b'openai-organization', b'user-ub6kcjjgjcqflrzwnh3ekrmh'), (b'openai-processing-ms', b'657'), (b'openai-version', b'2020-10-01'), (b'x-ratelimit-limit-requests', b'10000'), (b'x-ratelimit-limit-tokens', b'200000'), (b'x-ratelimit-remaining-requests', b'9999'), (b'x-ratelimit-remaining-tokens', b'199571'), (b'x-ratelimit-reset-requests', b'8.64s'), (b'x-ratelimit-reset-tokens', b'128ms'), (b'x-request-id', b'req_2ab783b8cabf9582819d9df2c9735819'), (b'strict-transport-security', b'max-age=31536000; includeSubDomains; preload'), (b'cf-cache-status', b'DYNAMIC'), (b'Set-Cookie', b'__cf_bm=yH2paz5u6vmoBDhWxYe4AB_slBn5ieQTi3kwdooomCY-1745853268-1.0.1.1-ll.q6w8vBCeTOq7JZWGV8Q_JR_0frio_bLaaeuFrsmbpTBNoY.uAcUIzxM_9iBLQ0vWRNOVU8YmfEeA1e0Bu1pqsFBI_X4jkd2je01sJYOU; path=/; expires=Mon, 28-Apr-25 15:44:28 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None'), (b'X-Content-Type-Options', b'nosniff'), (b'Set-Cookie', b'_cfuvid=LcR3ycnecRHUuJkOBpSo8u5Z50DeVq4s2_DXgS1oVwA-1745853268023-0.0.1.1-604800000; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None'), (b'Server', b'cloudflare'), (b'CF-RAY', b'937782610db6eb51-CPH'), (b'alt-svc', b'h3=":443"; ma=86400')])
2025-04-28 15:14:28,168 - [Worker-7] - _client.py:1038 - _send_single_request - INFO - HTTP Request: POST https://api.openai.com/v1/audio/speech "HTTP/1.1 200 OK"
2025-04-28 15:14:28,168 - [Worker-7] - _trace.py:47 - trace - DEBUG - receive_response_body.started request=<Request [b'POST']>
2025-04-28 15:14:43,490 - [Worker-7] - _trace.py:47 - trace - DEBUG - receive_response_body.complete
2025-04-28 15:14:43,490 - [Worker-7] - _trace.py:47 - trace - DEBUG - response_closed.started
2025-04-28 15:14:43,490 - [Worker-7] - _trace.py:47 - trace - DEBUG - response_closed.complete
2025-04-28 15:14:43,492 - [Worker-7] - _base_client.py:991 - _request - DEBUG - HTTP Response: POST https://api.openai.com/v1/audio/speech "200 OK" Headers([('date', 'Mon, 28 Apr 2025 15:14:28 GMT'), ('content-type', 'audio/mpeg'), ('transfer-encoding', 'chunked'), ('connection', 'keep-alive'), ('access-control-expose-headers', 'X-Request-ID'), ('openai-organization', 'user-ub6kcjjgjcqflrzwnh3ekrmh'), ('openai-processing-ms', '657'), ('openai-version', '2020-10-01'), ('x-ratelimit-limit-requests', '10000'), ('x-ratelimit-limit-tokens', '200000'), ('x-ratelimit-remaining-requests', '9999'), ('x-ratelimit-remaining-tokens', '199571'), ('x-ratelimit-reset-requests', '8.64s'), ('x-ratelimit-reset-tokens', '128ms'), ('x-request-id', 'req_2ab783b8cabf9582819d9df2c9735819'), ('strict-transport-security', 'max-age=31536000; includeSubDomains; preload'), ('cf-cache-status', 'DYNAMIC'), ('set-cookie', '__cf_bm=yH2paz5u6vmoBDhWxYe4AB_slBn5ieQTi3kwdooomCY-1745853268-1.0.1.1-ll.q6w8vBCeTOq7JZWGV8Q_JR_0frio_bLaaeuFrsmbpTBNoY.uAcUIzxM_9iBLQ0vWRNOVU8YmfEeA1e0Bu1pqsFBI_X4jkd2je01sJYOU; path=/; expires=Mon, 28-Apr-25 15:44:28 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None'), ('x-content-type-options', 'nosniff'), ('set-cookie', '_cfuvid=LcR3ycnecRHUuJkOBpSo8u5Z50DeVq4s2_DXgS1oVwA-1745853268023-0.0.1.1-604800000; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None'), ('server', 'cloudflare'), ('cf-ray', '937782610db6eb51-CPH'), ('alt-svc', 'h3=":443"; ma=86400')])
2025-04-28 15:14:43,492 - [Worker-7] - _base_client.py:999 - _request - DEBUG - request_id: req_2ab783b8cabf9582819d9df2c9735819
2025-04-28 15:14:43,492 - [Worker-7] - openai_tts_provider.py:88 - text_to_speech - DEBUG - Remote server response: status_code=200, size=1651200 bytes, content=b'\xff\xf3\xc4\xc4\x00Z\xd49\xe0\x00\xde0\xdc;D\x03m\xd1<\xb7\xd3+\x192\xb0SF\x908\xc3\xc3\x13=31p 9\x8e\x8b\x82\x83\xcb>\x02\x03,\x99\x81\x81\x98\x08\tk\xd0\x00\xae#\t\xa0Y\x02\xd0"\xa2*)\xa3\xaf\r\xb5\xb6\x1e\xa9\xd4\r\x13\xd0}u\xb2\xc6\xb0\xb0\x8b\xb1v2\xc8q\xd8]\x8a\x0e\xbb\xd1=\x00j\x0e\xbb\xd8\x9b\xbf/\xb1\x84\xdb\xff\x1b\x87\xe3\x8e\xe4\xb1\xdb\x87\xe3mn\x0fp\x1dH-\xdfV\xc0'...
2025-04-28 15:14:43,492 - [Worker-7] - openai_tts_provider.py:70 - text_to_speech - INFO - Processing chapter-1_A chap name_chunk_2_of_11, length=1513
2025-04-28 15:14:43,492 - [Worker-7] - openai_tts_provider.py:73 - text_to_speech - DEBUG - Processing chapter-1_A chap name_chunk_2_of_11, length=1513, text=[TEXT]
2025-04-28 15:14:43,493 - [Worker-7] - _base_client.py:453 - _build_request - DEBUG - Request options: {'method': 'post', 'url': '/audio/speech', 'headers': {'Accept': 'application/octet-stream'}, 'files': None, 'json_data': {'input': 'TEXT', 'model': 'gpt-4o-mini-tts', 'voice': 'alloy', 'instructions': 'normal voice', 'response_format': 'mp3', 'speed': 1.0}}
2025-04-28 15:14:43,494 - [Worker-7] - _base_client.py:952 - _request - DEBUG - Sending HTTP Request: POST https://api.openai.com/v1/audio/speech
2025-04-28 15:14:43,495 - [Worker-7] - _trace.py:47 - trace - DEBUG - send_request_headers.started request=<Request [b'POST']>
2025-04-28 15:14:43,495 - [Worker-7] - _trace.py:47 - trace - DEBUG - send_request_headers.complete
2025-04-28 15:14:43,495 - [Worker-7] - _trace.py:47 - trace - DEBUG - send_request_body.started request=<Request [b'POST']>
2025-04-28 15:14:43,496 - [Worker-7] - _trace.py:47 - trace - DEBUG - send_request_body.complete
2025-04-28 15:14:43,496 - [Worker-7] - _trace.py:47 - trace - DEBUG - receive_response_headers.started request=<Request [b'POST']>
2025-04-28 15:14:45,059 - [Worker-7] - _trace.py:47 - trace - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Mon, 28 Apr 2025 15:14:44 GMT'), (b'Content-Type', b'audio/mpeg'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'access-control-expose-headers', b'X-Request-ID'), (b'openai-organization', b'user-ub6kcjjgjcqflrzwnh3ekrmh'), (b'openai-processing-ms', b'1030'), (b'openai-version', b'2020-10-01'), (b'x-ratelimit-limit-requests', b'10000'), (b'x-ratelimit-limit-tokens', b'200000'), (b'x-ratelimit-remaining-requests', b'9999'), (b'x-ratelimit-remaining-tokens', b'199611'), (b'x-ratelimit-reset-requests', b'8.64s'), (b'x-ratelimit-reset-tokens', b'116ms'), (b'x-request-id', b'req_5cc3ada380bdabadedfea9e0bc3cef21'), (b'strict-transport-security', b'max-age=31536000; includeSubDomains; preload'), (b'cf-cache-status', b'DYNAMIC'), (b'X-Content-Type-Options', b'nosniff'), (b'Server', b'cloudflare'), (b'CF-RAY', b'937782cd097aeb51-CPH'), (b'alt-svc', b'h3=":443"; ma=86400')])
2025-04-28 15:14:45,061 - [Worker-7] - _client.py:1038 - _send_single_request - INFO - HTTP Request: POST https://api.openai.com/v1/audio/speech "HTTP/1.1 200 OK"
2025-04-28 15:14:45,062 - [Worker-7] - _trace.py:47 - trace - DEBUG - receive_response_body.started request=<Request [b'POST']>
2025-04-28 15:15:05,547 - [Worker-7] - _trace.py:47 - trace - DEBUG - receive_response_body.complete
2025-04-28 15:15:05,547 - [Worker-7] - _trace.py:47 - trace - DEBUG - response_closed.started
2025-04-28 15:15:05,547 - [Worker-7] - _trace.py:47 - trace - DEBUG - response_closed.complete
2025-04-28 15:15:05,549 - [Worker-7] - _base_client.py:991 - _request - DEBUG - HTTP Response: POST https://api.openai.com/v1/audio/speech "200 OK" Headers({'date': 'Mon, 28 Apr 2025 15:14:44 GMT', 'content-type': 'audio/mpeg', 'transfer-encoding': 'chunked', 'connection': 'keep-alive', 'access-control-expose-headers': 'X-Request-ID', 'openai-organization': 'user-ub6kcjjgjcqflrzwnh3ekrmh', 'openai-processing-ms': '1030', 'openai-version': '2020-10-01', 'x-ratelimit-limit-requests': '10000', 'x-ratelimit-limit-tokens': '200000', 'x-ratelimit-remaining-requests': '9999', 'x-ratelimit-remaining-tokens': '199611', 'x-ratelimit-reset-requests': '8.64s', 'x-ratelimit-reset-tokens': '116ms', 'x-request-id': 'req_5cc3ada380bdabadedfea9e0bc3cef21', 'strict-transport-security': 'max-age=31536000; includeSubDomains; preload', 'cf-cache-status': 'DYNAMIC', 'x-content-type-options': 'nosniff', 'server': 'cloudflare', 'cf-ray': '937782cd097aeb51-CPH', 'alt-svc': 'h3=":443"; ma=86400'})
2025-04-28 15:15:05,549 - [Worker-7] - _base_client.py:999 - _request - DEBUG - request_id: req_5cc3ada380bdabadedfea9e0bc3cef21
2025-04-28 15:15:05,549 - [Worker-7] - openai_tts_provider.py:88 - text_to_speech - DEBUG - Remote server response: status_code=200, size=1566720 bytes, content=b'\xff\xf3\xc4\xc4\x00Z\x9c9\xd4\x01Y\xc8\x002\xcf5]8\xe9:\xe98\xd9\x016\xd6\x81\x00\x18\x80\x18\xe1\x98`\x96\x8d0\xd7z\xa7LtWH\xb4\x1cED$ \x10\xb9\x05\xc8@"\x0e&\x02E\xa6:c\xa2\xb9w\xcb\x96^4\xc3u\xe8ct\xf1\xb7m\x9d\xb3\xb6\xbf\x0f\xcb%\x0f\xe3\x90\xe4?\x90\xe5\'>\xbc\xae\x1b\x7f\xe3r\xfe\xe1o:\x92\x87\xf1\xc8\x87*\xb5\xb4\xc4LD\xc4T\x8b\x11\xae;\x8e\xc38T\xecM\xdf'...
2025-04-28 15:15:05,549 - [Worker-7] - openai_tts_provider.py:70 - text_to_speech - INFO - Processing chapter-1_A chap name_chunk_3_of_11, length=1740
2025-04-28 15:15:05,549 - [Worker-7] - openai_tts_provider.py:73 - text_to_speech - DEBUG - Processing chapter-1_A chap name_chunk_3_of_11, length=1740, text=[TEXT]
2025-04-28 15:15:05,551 - [Worker-7] - _base_client.py:453 - _build_request - DEBUG - Request options: {'method': 'post', 'url': '/audio/speech', 'headers': {'Accept': 'application/octet-stream'}, 'files': None, 'json_data': {'input': 'TEXT', 'model': 'gpt-4o-mini-tts', 'voice': 'alloy', 'instructions': 'normal voice', 'response_format': 'mp3', 'speed': 1.0}}
2025-04-28 15:15:05,552 - [Worker-7] - _base_client.py:952 - _request - DEBUG - Sending HTTP Request: POST https://api.openai.com/v1/audio/speech
2025-04-28 15:15:05,553 - [Worker-7] - _trace.py:47 - trace - DEBUG - send_request_headers.started request=<Request [b'POST']>
2025-04-28 15:15:05,553 - [Worker-7] - _trace.py:47 - trace - DEBUG - send_request_headers.complete
2025-04-28 15:15:05,553 - [Worker-7] - _trace.py:47 - trace - DEBUG - send_request_body.started request=<Request [b'POST']>
2025-04-28 15:15:05,554 - [Worker-7] - _trace.py:47 - trace - DEBUG - send_request_body.complete
2025-04-28 15:15:05,554 - [Worker-7] - _trace.py:47 - trace - DEBUG - receive_response_headers.started request=<Request [b'POST']>
2025-04-28 15:15:07,909 - [Worker-7] - _trace.py:47 - trace - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Mon, 28 Apr 2025 15:15:07 GMT'), (b'Content-Type', b'audio/mpeg'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'access-control-expose-headers', b'X-Request-ID'), (b'openai-organization', b'user-ub6kcjjgjcqflrzwnh3ekrmh'), (b'openai-processing-ms', b'1536'), (b'openai-version', b'2020-10-01'), (b'x-ratelimit-limit-requests', b'10000'), (b'x-ratelimit-limit-tokens', b'200000'), (b'x-ratelimit-remaining-requests', b'9999'), (b'x-ratelimit-remaining-tokens', b'199551'), (b'x-ratelimit-reset-requests', b'8.64s'), (b'x-ratelimit-reset-tokens', b'134ms'), (b'x-request-id', b'req_bf51132a53cc4d10821fa0f767e2d64d'), (b'strict-transport-security', b'max-age=31536000; includeSubDomains; preload'), (b'cf-cache-status', b'DYNAMIC'), (b'X-Content-Type-Options', b'nosniff'), (b'Server', b'cloudflare'), (b'CF-RAY', b'93778356ecb1eb51-CPH'), (b'alt-svc', b'h3=":443"; ma=86400')])
2025-04-28 15:15:07,911 - [Worker-7] - _client.py:1038 - _send_single_request - INFO - HTTP Request: POST https://api.openai.com/v1/audio/speech "HTTP/1.1 200 OK"
2025-04-28 15:15:07,911 - [Worker-7] - _trace.py:47 - trace - DEBUG - receive_response_body.started request=<Request [b'POST']>
2025-04-28 15:16:13,739 - [Worker-7] - _trace.py:47 - trace - DEBUG - receive_response_body.complete
2025-04-28 15:16:13,739 - [Worker-7] - _trace.py:47 - trace - DEBUG - response_closed.started
2025-04-28 15:16:13,740 - [Worker-7] - _trace.py:47 - trace - DEBUG - response_closed.complete
2025-04-28 15:16:13,746 - [Worker-7] - _base_client.py:991 - _request - DEBUG - HTTP Response: POST https://api.openai.com/v1/audio/speech "200 OK" Headers({'date': 'Mon, 28 Apr 2025 15:15:07 GMT', 'content-type': 'audio/mpeg', 'transfer-encoding': 'chunked', 'connection': 'keep-alive', 'access-control-expose-headers': 'X-Request-ID', 'openai-organization': 'user-ub6kcjjgjcqflrzwnh3ekrmh', 'openai-processing-ms': '1536', 'openai-version': '2020-10-01', 'x-ratelimit-limit-requests': '10000', 'x-ratelimit-limit-tokens': '200000', 'x-ratelimit-remaining-requests': '9999', 'x-ratelimit-remaining-tokens': '199551', 'x-ratelimit-reset-requests': '8.64s', 'x-ratelimit-reset-tokens': '134ms', 'x-request-id': 'req_bf51132a53cc4d10821fa0f767e2d64d', 'strict-transport-security': 'max-age=31536000; includeSubDomains; preload', 'cf-cache-status': 'DYNAMIC', 'x-content-type-options': 'nosniff', 'server': 'cloudflare', 'cf-ray': '93778356ecb1eb51-CPH', 'alt-svc': 'h3=":443"; ma=86400'})
2025-04-28 15:16:13,747 - [Worker-7] - _base_client.py:999 - _request - DEBUG - request_id: req_bf51132a53cc4d10821fa0f767e2d64d
2025-04-28 15:16:13,748 - [Worker-7] - openai_tts_provider.py:88 - text_to_speech - DEBUG - Remote server response: status_code=200, size=1858560 bytes, content=b'\xff\xf3\xc4\xc4\x00[\x149\xe4\x00\xe60\xdc6\xe1\x90\xcf\xf1S\x8b\xa5L\x08@1\x10\xa0\xcb\x05\xe0\x82\x88\x08.\xdf\x16\xcc\x02\t0\x885Q\xaas\x01\x08\x0c\x08\x1b\x16+\x11\x10\x0ch\x16N#\x0e\x08\x0c\x18\x0e\x01\xa1\x00\xe0\xc5\x04\x11"\x19=\xaa\xf153Er\xe5\xa0\xfb\x07r\x1c\x86\x19\x08t Vd\x9f\x102\x00\xd9[\xbc\x81c\xc7. \x84*\x99v\xa5\n\x03\xd112\xd7r\x96M1\n\x18\xc3?^\xf2\xc8n'...
2025-04-28 15:16:13,748 - [Worker-7] - openai_tts_provider.py:70 - text_to_speech - INFO - Processing chapter-1_A chap name_chunk_4_of_11, length=1737
2025-04-28 15:16:13,748 - [Worker-7] - openai_tts_provider.py:73 - text_to_speech - DEBUG - Processing chapter-1_A chap name_chunk_4_of_11, length=1737, text=[TEXT]
2025-04-28 15:16:13,752 - [Worker-7] - _base_client.py:453 - _build_request - DEBUG - Request options: {'method': 'post', 'url': '/audio/speech', 'headers': {'Accept': 'application/octet-stream'}, 'files': None, 'json_data': {'input': 'TEXT', 'model': 'gpt-4o-mini-tts', 'voice': 'alloy', 'instructions': 'normal voice', 'response_format': 'mp3', 'speed': 1.0}}
2025-04-28 15:16:13,755 - [Worker-7] - _base_client.py:952 - _request - DEBUG - Sending HTTP Request: POST https://api.openai.com/v1/audio/speech
2025-04-28 15:16:13,756 - [Worker-7] - _trace.py:47 - trace - DEBUG - send_request_headers.started request=<Request [b'POST']>
2025-04-28 15:16:13,757 - [Worker-7] - _trace.py:47 - trace - DEBUG - send_request_headers.complete
2025-04-28 15:16:13,757 - [Worker-7] - _trace.py:47 - trace - DEBUG - send_request_body.started request=<Request [b'POST']>
2025-04-28 15:16:13,758 - [Worker-7] - _trace.py:47 - trace - DEBUG - send_request_body.complete
2025-04-28 15:16:13,758 - [Worker-7] - _trace.py:47 - trace - DEBUG - receive_response_headers.started request=<Request [b'POST']>
2025-04-28 15:16:14,711 - [Worker-7] - _trace.py:47 - trace - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Mon, 28 Apr 2025 15:16:14 GMT'), (b'Content-Type', b'audio/mpeg'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'access-control-expose-headers', b'X-Request-ID'), (b'openai-organization', b'user-ub6kcjjgjcqflrzwnh3ekrmh'), (b'openai-processing-ms', b'779'), (b'openai-version', b'2020-10-01'), (b'x-ratelimit-limit-requests', b'10000'), (b'x-ratelimit-limit-tokens', b'200000'), (b'x-ratelimit-remaining-requests', b'9999'), (b'x-ratelimit-remaining-tokens', b'199556'), (b'x-ratelimit-reset-requests', b'8.64s'), (b'x-ratelimit-reset-tokens', b'133ms'), (b'x-request-id', b'req_00fd5f9f46a2a0e6e0be2fdda8e72bb1'), (b'strict-transport-security', b'max-age=31536000; includeSubDomains; preload'), (b'cf-cache-status', b'DYNAMIC'), (b'X-Content-Type-Options', b'nosniff'), (b'Server', b'cloudflare'), (b'CF-RAY', b'937785012ffdeb51-CPH'), (b'alt-svc', b'h3=":443"; ma=86400')])
2025-04-28 15:16:14,713 - [Worker-7] - _client.py:1038 - _send_single_request - INFO - HTTP Request: POST https://api.openai.com/v1/audio/speech "HTTP/1.1 200 OK"
2025-04-28 15:16:14,713 - [Worker-7] - _trace.py:47 - trace - DEBUG - receive_response_body.started request=<Request [b'POST']>
2025-04-28 15:16:30,890 - [Worker-7] - _trace.py:47 - trace - DEBUG - receive_response_body.complete
2025-04-28 15:16:30,890 - [Worker-7] - _trace.py:47 - trace - DEBUG - response_closed.started
2025-04-28 15:16:30,890 - [Worker-7] - _trace.py:47 - trace - DEBUG - response_closed.complete
2025-04-28 15:16:30,892 - [Worker-7] - _base_client.py:991 - _request - DEBUG - HTTP Response: POST https://api.openai.com/v1/audio/speech "200 OK" Headers({'date': 'Mon, 28 Apr 2025 15:16:14 GMT', 'content-type': 'audio/mpeg', 'transfer-encoding': 'chunked', 'connection': 'keep-alive', 'access-control-expose-headers': 'X-Request-ID', 'openai-organization': 'user-ub6kcjjgjcqflrzwnh3ekrmh', 'openai-processing-ms': '779', 'openai-version': '2020-10-01', 'x-ratelimit-limit-requests': '10000', 'x-ratelimit-limit-tokens': '200000', 'x-ratelimit-remaining-requests': '9999', 'x-ratelimit-remaining-tokens': '199556', 'x-ratelimit-reset-requests': '8.64s', 'x-ratelimit-reset-tokens': '133ms', 'x-request-id': 'req_00fd5f9f46a2a0e6e0be2fdda8e72bb1', 'strict-transport-security': 'max-age=31536000; includeSubDomains; preload', 'cf-cache-status': 'DYNAMIC', 'x-content-type-options': 'nosniff', 'server': 'cloudflare', 'cf-ray': '937785012ffdeb51-CPH', 'alt-svc': 'h3=":443"; ma=86400'})
2025-04-28 15:16:30,892 - [Worker-7] - _base_client.py:999 - _request - DEBUG - request_id: req_00fd5f9f46a2a0e6e0be2fdda8e72bb1
2025-04-28 15:16:30,892 - [Worker-7] - openai_tts_provider.py:88 - text_to_speech - DEBUG - Remote server response: status_code=200, size=1673088 bytes, content=b'\xff\xf3\xc4\xc4\x00[\xbc9\xc8\x01Y\xc0\x00:i9\xe58[5M\x07\x16\xed\x16\xa0\xc4 \xca\x18\xd1,\xcb$\xc5\x0c\xb3e\xb7-8\x043\x14\x934\xb3acQCH\xe30\xc3(\xa3 \x83\x18"\xd63H\x83\xf12\xca\xd2\x1c\xbb\xe5\xcbE6_\x14\xa4\x94F#\x11\x88\xc5%\x8e\xcc;\x0eC\x90\xfeC\x0c\xa1!\x0c!\x01\x0c\xb3h\x03Sw~\xd4\xa1\xfc\x7f\xe5\xf7%\x11\x8b\xd15\xce\x80p\x10\x0c\x00,\xc1m\x11A'...
2025-04-28 15:16:30,892 - [Worker-7] - openai_tts_provider.py:70 - text_to_speech - INFO - Processing chapter-1_A chap name_chunk_5_of_11, length=1700
2025-04-28 15:16:30,892 - [Worker-7] - openai_tts_provider.py:73 - text_to_speech - DEBUG - Processing chapter-1_A chap name_chunk_5_of_11, length=1700, text=[TEXT]
2025-04-28 15:16:30,893 - [Worker-7] - _base_client.py:453 - _build_request - DEBUG - Request options: {'method': 'post', 'url': '/audio/speech', 'headers': {'Accept': 'application/octet-stream'}, 'files': None, 'json_data': {'input': TEXT', 'model': 'gpt-4o-mini-tts', 'voice': 'alloy', 'instructions': 'normal voice', 'response_format': 'mp3', 'speed': 1.0}}
2025-04-28 15:16:30,894 - [Worker-7] - _base_client.py:952 - _request - DEBUG - Sending HTTP Request: POST https://api.openai.com/v1/audio/speech
2025-04-28 15:16:30,895 - [Worker-7] - _trace.py:47 - trace - DEBUG - send_request_headers.started request=<Request [b'POST']>
2025-04-28 15:16:30,895 - [Worker-7] - _trace.py:47 - trace - DEBUG - send_request_headers.complete
2025-04-28 15:16:30,895 - [Worker-7] - _trace.py:47 - trace - DEBUG - send_request_body.started request=<Request [b'POST']>
2025-04-28 15:16:30,896 - [Worker-7] - _trace.py:47 - trace - DEBUG - send_request_body.complete
2025-04-28 15:16:30,896 - [Worker-7] - _trace.py:47 - trace - DEBUG - receive_response_headers.started request=<Request [b'POST']>
2025-04-28 15:16:31,924 - [Worker-7] - _trace.py:47 - trace - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Mon, 28 Apr 2025 15:16:31 GMT'), (b'Content-Type', b'audio/mpeg'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'access-control-expose-headers', b'X-Request-ID'), (b'openai-organization', b'user-ub6kcjjgjcqflrzwnh3ekrmh'), (b'openai-processing-ms', b'757'), (b'openai-version', b'2020-10-01'), (b'x-ratelimit-limit-requests', b'10000'), (b'x-ratelimit-limit-tokens', b'200000'), (b'x-ratelimit-remaining-requests', b'9999'), (b'x-ratelimit-remaining-tokens', b'199563'), (b'x-ratelimit-reset-requests', b'8.64s'), (b'x-ratelimit-reset-tokens', b'130ms'), (b'x-request-id', b'req_e4d35a4eb588c1ff2781d635f4c97c45'), (b'strict-transport-security', b'max-age=31536000; includeSubDomains; preload'), (b'cf-cache-status', b'DYNAMIC'), (b'X-Content-Type-Options', b'nosniff'), (b'Server', b'cloudflare'), (b'CF-RAY', b'9377856c4b4feb51-CPH'), (b'alt-svc', b'h3=":443"; ma=86400')])
2025-04-28 15:16:31,926 - [Worker-7] - _client.py:1038 - _send_single_request - INFO - HTTP Request: POST https://api.openai.com/v1/audio/speech "HTTP/1.1 200 OK"
2025-04-28 15:16:31,927 - [Worker-7] - _trace.py:47 - trace - DEBUG - receive_response_body.started request=<Request [b'POST']>
2025-04-28 15:16:49,255 - [Worker-7] - _trace.py:47 - trace - DEBUG - receive_response_body.complete
2025-04-28 15:16:49,255 - [Worker-7] - _trace.py:47 - trace - DEBUG - response_closed.started
2025-04-28 15:16:49,255 - [Worker-7] - _trace.py:47 - trace - DEBUG - response_closed.complete
2025-04-28 15:16:49,258 - [Worker-7] - _base_client.py:991 - _request - DEBUG - HTTP Response: POST https://api.openai.com/v1/audio/speech "200 OK" Headers({'date': 'Mon, 28 Apr 2025 15:16:31 GMT', 'content-type': 'audio/mpeg', 'transfer-encoding': 'chunked', 'connection': 'keep-alive', 'access-control-expose-headers': 'X-Request-ID', 'openai-organization': 'user-ub6kcjjgjcqflrzwnh3ekrmh', 'openai-processing-ms': '757', 'openai-version': '2020-10-01', 'x-ratelimit-limit-requests': '10000', 'x-ratelimit-limit-tokens': '200000', 'x-ratelimit-remaining-requests': '9999', 'x-ratelimit-remaining-tokens': '199563', 'x-ratelimit-reset-requests': '8.64s', 'x-ratelimit-reset-tokens': '130ms', 'x-request-id': 'req_e4d35a4eb588c1ff2781d635f4c97c45', 'strict-transport-security': 'max-age=31536000; includeSubDomains; preload', 'cf-cache-status': 'DYNAMIC', 'x-content-type-options': 'nosniff', 'server': 'cloudflare', 'cf-ray': '9377856c4b4feb51-CPH', 'alt-svc': 'h3=":443"; ma=86400'})
2025-04-28 15:16:49,258 - [Worker-7] - _base_client.py:999 - _request - DEBUG - request_id: req_e4d35a4eb588c1ff2781d635f4c97c45
2025-04-28 15:16:49,258 - [Worker-7] - openai_tts_provider.py:88 - text_to_speech - DEBUG - Remote server response: status_code=200, size=1912320 bytes, content=b'\xff\xf3\xc4\xc4\x00Z\x1c9\xc4\x01Z\xc0\x002fM+3\x7f\x1c\xe5\xc77\xabL\xc8\x11\xc0F8\x91\x8e\x0c\x02\x1eY2\xcd\xa0\xfac\xa6:+\xa4Z\xebk\x8daL\x10\x90\\\x82\xe4\x17!\x07\x14\x11M\xd7z\xa7P4W@:\x01\xd3\x0e\x07\x95\xcb\xe6\x1f\xc7\xf2\x1c\xb1v6\xfe9\x0f\xe49,\xe6\xa2\x0c\xe11\xd2-S\xb17-\xff\x8d\xc3nZ\xecg\x0e\xe4\xb3\x99\xd3\xc3nZ\xecXEH\xa9\x15"\xeck\x8eC\x90'...
2025-04-28 15:16:49,258 - [Worker-7] - openai_tts_provider.py:70 - text_to_speech - INFO - Processing chapter-1_A chap name_chunk_6_of_11, length=1753


[I TRUNCATED IT HERE SINCE IT IS ALL THE SAME]


2025-04-28 15:18:52,849 - [Worker-7] - _base_client.py:952 - _request - DEBUG - Sending HTTP Request: POST https://api.openai.com/v1/audio/speech
2025-04-28 15:18:52,850 - [Worker-7] - _trace.py:47 - trace - DEBUG - send_request_headers.started request=<Request [b'POST']>
2025-04-28 15:18:52,853 - [Worker-7] - _trace.py:47 - trace - DEBUG - send_request_headers.complete
2025-04-28 15:18:52,855 - [Worker-7] - _trace.py:47 - trace - DEBUG - send_request_body.started request=<Request [b'POST']>
2025-04-28 15:18:52,859 - [Worker-7] - _trace.py:47 - trace - DEBUG - send_request_body.complete
2025-04-28 15:18:52,859 - [Worker-7] - _trace.py:47 - trace - DEBUG - receive_response_headers.started request=<Request [b'POST']>
2025-04-28 15:18:54,127 - [Worker-7] - _trace.py:47 - trace - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Mon, 28 Apr 2025 15:18:53 GMT'), (b'Content-Type', b'audio/mpeg'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'access-control-expose-headers', b'X-Request-ID'), (b'openai-organization', b'user-ub6kcjjgjcqflrzwnh3ekrmh'), (b'openai-processing-ms', b'799'), (b'openai-version', b'2020-10-01'), (b'x-ratelimit-limit-requests', b'10000'), (b'x-ratelimit-limit-tokens', b'200000'), (b'x-ratelimit-remaining-requests', b'9999'), (b'x-ratelimit-remaining-tokens', b'199642'), (b'x-ratelimit-reset-requests', b'8.64s'), (b'x-ratelimit-reset-tokens', b'107ms'), (b'x-request-id', b'req_666ab9d18ed812c49647ab8feb82f91b'), (b'strict-transport-security', b'max-age=31536000; includeSubDomains; preload'), (b'cf-cache-status', b'DYNAMIC'), (b'X-Content-Type-Options', b'nosniff'), (b'Server', b'cloudflare'), (b'CF-RAY', b'937788e37f1beb51-CPH'), (b'alt-svc', b'h3=":443"; ma=86400')])
2025-04-28 15:18:54,127 - [Worker-7] - _client.py:1038 - _send_single_request - INFO - HTTP Request: POST https://api.openai.com/v1/audio/speech "HTTP/1.1 200 OK"
2025-04-28 15:18:54,128 - [Worker-7] - _trace.py:47 - trace - DEBUG - receive_response_body.started request=<Request [b'POST']>
2025-04-28 15:19:06,559 - [Worker-7] - _trace.py:47 - trace - DEBUG - receive_response_body.complete
2025-04-28 15:19:06,559 - [Worker-7] - _trace.py:47 - trace - DEBUG - response_closed.started
2025-04-28 15:19:06,559 - [Worker-7] - _trace.py:47 - trace - DEBUG - response_closed.complete
2025-04-28 15:19:06,561 - [Worker-7] - _base_client.py:991 - _request - DEBUG - HTTP Response: POST https://api.openai.com/v1/audio/speech "200 OK" Headers({'date': 'Mon, 28 Apr 2025 15:18:53 GMT', 'content-type': 'audio/mpeg', 'transfer-encoding': 'chunked', 'connection': 'keep-alive', 'access-control-expose-headers': 'X-Request-ID', 'openai-organization': 'user-ub6kcjjgjcqflrzwnh3ekrmh', 'openai-processing-ms': '799', 'openai-version': '2020-10-01', 'x-ratelimit-limit-requests': '10000', 'x-ratelimit-limit-tokens': '200000', 'x-ratelimit-remaining-requests': '9999', 'x-ratelimit-remaining-tokens': '199642', 'x-ratelimit-reset-requests': '8.64s', 'x-ratelimit-reset-tokens': '107ms', 'x-request-id': 'req_666ab9d18ed812c49647ab8feb82f91b', 'strict-transport-security': 'max-age=31536000; includeSubDomains; preload', 'cf-cache-status': 'DYNAMIC', 'x-content-type-options': 'nosniff', 'server': 'cloudflare', 'cf-ray': '937788e37f1beb51-CPH', 'alt-svc': 'h3=":443"; ma=86400'})
2025-04-28 15:19:06,561 - [Worker-7] - _base_client.py:999 - _request - DEBUG - request_id: req_666ab9d18ed812c49647ab8feb82f91b
2025-04-28 15:19:06,562 - [Worker-7] - openai_tts_provider.py:88 - text_to_speech - DEBUG - Remote server response: status_code=200, size=1418496 bytes, content=b'\xff\xf3\xc4\xc4\x00\\T9\xd4\x00\xde2\xdc8\xe5\x03\x0fo8V\x93MM40\x13.@\x1690\xb0\xf3\x0f\x03W\xa0\x90P\xc0:t\x05\x96m\x07\xd2\x1d:\xd6\x11\x15\x16"& \x11"\x16$R\xbb\xf8\xfcAl\xed\xfb\x86\xd5\xbd"\xddx\xfc\x8eX\xfb\xc4\x99\xc2\xc20G\x010\xe0wM!\xd4\xde\x07\xb8\xec9\x0c=\x04\xe5\xdbq\xd5\xbd0\xe1\xa8\xa5f\x1f\x0f:\x8c\xad\xdeT\x8f\x93[\x87\xda@ F@%c\xb9'...
2025-04-28 15:19:06,562 - [Worker-7] - utils.py:274 - merge_audio_segments - INFO - Using direct write to merge audio segments: ['chapter-1_A chap name_chunk_1_of_11', 'chapter-1_A chap name_chunk_2_of_11', 'chapter-1_A chap name_chunk_3_of_11', 'chapter-1_A chap name_chunk_4_of_11', 'chapter-1_A chap name_chunk_5_of_11', 'chapter-1_A chap name_chunk_6_of_11', 'chapter-1_A chap name_chunk_7_of_11', 'chapter-1_A chap name_chunk_8_of_11', 'chapter-1_A chap name_chunk_9_of_11', 'chapter-1_A chap name_chunk_10_of_11', 'chapter-1_A chap name_chunk_11_of_11']
2025-04-28 15:19:06,562 - [Worker-7] - utils.py:244 - direct_merge_audio_segments - DEBUG - Writing audio segments directly to file: audiobook_output/0001_a file.mp3
2025-04-28 15:19:06,741 - [Worker-7] - utils.py:249 - direct_merge_audio_segments - DEBUG - Direct writing completed: audiobook_output/0001_a file.mp3
2025-04-28 15:19:06,744 - [Worker-7] - utils.py:155 - set_audio_tags - DEBUG - handling ID3NoHeaderError: audiobook_output/0001_a file.mp3
2025-04-28 15:19:06,972 - [Worker-7] - audiobook_generator.py:83 - process_chapter - INFO - ✅ Converted chapter 1: A chap name, output file: audiobook_output/0001_a file.mp3
2025-04-28 15:19:06,981 - audiobook_generator.py:176 - run - INFO - All chapters converted successfully. 🎉🎉🎉

Without instructions

docker run -i -t --rm -v D:/Downloads/:/app -e OPENAI_API_KEY=NOOOOO ghcr.io/p0n1/epub_to_audiobook "my.epub" audiobook_output --tts openai --log DEBUG
Starting entrypoint script...
Executing default command: python3 /app_src/main.py my.epub audiobook_output --tts openai --log DEBUG
/usr/local/lib/python3.11/site-packages/ebooklib/epub.py:1423: FutureWarning: This search incorrectly ignores the root element, and will be fixed in a future version.  If you rely on the current behaviour, change it to './/xmlns:rootfile[@media-type]'
  for root_file in tree.findall('//xmlns:rootfile[@media-type]', namespaces={'xmlns': NAMESPACES['CONTAINERNS']}):
2025-04-28 16:44:11,187 - _config.py:82 - load_ssl_context - DEBUG - load_ssl_context verify=True cert=None trust_env=True http2=False
2025-04-28 16:44:11,210 - _config.py:148 - load_ssl_context_verify - DEBUG - load_verify_locations cafile='/usr/local/lib/python3.11/site-packages/certifi/cacert.pem'
2025-04-28 16:44:11,348 - epub_book_parser.py:49 - get_chapters - DEBUG - Raw text: <

>
2025-04-28 16:44:11,348 - epub_book_parser.py:61 - get_chapters - DEBUG - Cleaned text step 1: <>
2025-04-28 16:44:11,348 - epub_book_parser.py:63 - get_chapters - DEBUG - Cleaned text step 2: <>
2025-04-28 16:44:11,348 - epub_book_parser.py:78 - get_chapters - DEBUG - Cleaned text step 5: <>
2025-04-28 16:44:11,348 - epub_book_parser.py:103 - get_chapters - DEBUG - Raw title: <>
2025-04-28 16:44:11,349 - epub_book_parser.py:105 - get_chapters - DEBUG - Sanitized title: <>
2025-04-28 16:44:11,353 - epub_book_parser.py:49 - get_chapters - DEBUG - Raw text: <



[TEXT]



>
2025-04-28 16:44:11,355 - epub_book_parser.py:61 - get_chapters - DEBUG - Cleaned text step 1: <chap name
[TEXT]

2025-04-28 16:44:11,358 - epub_book_parser.py:63 - get_chapters - DEBUG - Cleaned text step 2: <TEXT>
2025-04-28 16:44:11,359 - epub_book_parser.py:78 - get_chapters - DEBUG - Cleaned text step 5: <TEXT>
2025-04-28 16:44:11,360 - epub_book_parser.py:103 - get_chapters - DEBUG - Raw title: <chap name>
2025-04-28 16:44:11,360 - epub_book_parser.py:105 - get_chapters - DEBUG - Sanitized title: <A chap name>
2025-04-28 16:44:11,361 - audiobook_generator.py:105 - run - INFO - Chapters count: 1.
2025-04-28 16:44:11,361 - audiobook_generator.py:123 - run - INFO - Converting chapters from 1 to 1.
2025-04-28 16:44:11,361 - audiobook_generator.py:131 - run - INFO - ✨ Total characters in selected book chapters: 18437 ✨
Estimate book voiceover would cost you roughly: $0.06

Do you want to continue? (y/n)
y
2025-04-28 16:44:13,203 - [Worker-7] - audiobook_generator.py:60 - process_chapter - INFO - Processing chapter 1: A chap name
2025-04-28 16:44:13,206 - [Worker-7] - _config.py:82 - load_ssl_context - DEBUG - load_ssl_context verify=True cert=None trust_env=True http2=False
2025-04-28 16:44:13,208 - [Worker-7] - _config.py:148 - load_ssl_context_verify - DEBUG - load_verify_locations cafile='/usr/local/lib/python3.11/site-packages/certifi/cacert.pem'
2025-04-28 16:44:13,444 - [Worker-7] - openai_tts_provider.py:70 - text_to_speech - INFO - Processing chapter-1_A chap name_chunk_1_of_11, length=1670
2025-04-28 16:44:13,444 - [Worker-7] - openai_tts_provider.py:73 - text_to_speech - DEBUG - Processing chapter-1_A chap name_chunk_1_of_11, length=1670, text=[ TEXT]
2025-04-28 16:44:13,447 - [Worker-7] - _base_client.py:453 - _build_request - DEBUG - Request options: {'method': 'post', 'url': '/audio/speech', 'headers': {'Accept': 'application/octet-stream'}, 'files': None, 'json_data': {'input': ' TEXT', 'model': 'gpt-4o-mini-tts', 'voice': 'alloy', 'instructions': None, 'response_format': 'mp3', 'speed': 1.0}}
2025-04-28 16:44:13,487 - [Worker-7] - _base_client.py:952 - _request - DEBUG - Sending HTTP Request: POST https://api.openai.com/v1/audio/speech
2025-04-28 16:44:13,488 - [Worker-7] - _trace.py:47 - trace - DEBUG - connect_tcp.started host='api.openai.com' port=443 local_address=None timeout=5.0 socket_options=None
2025-04-28 16:44:13,564 - [Worker-7] - _trace.py:47 - trace - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x7f0d56fae490>
2025-04-28 16:44:13,565 - [Worker-7] - _trace.py:47 - trace - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x7f0d570dfb60> server_hostname='api.openai.com' timeout=5.0
2025-04-28 16:44:13,584 - [Worker-7] - _trace.py:47 - trace - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x7f0d56e60b90>
2025-04-28 16:44:13,584 - [Worker-7] - _trace.py:47 - trace - DEBUG - send_request_headers.started request=<Request [b'POST']>
2025-04-28 16:44:13,585 - [Worker-7] - _trace.py:47 - trace - DEBUG - send_request_headers.complete
2025-04-28 16:44:13,585 - [Worker-7] - _trace.py:47 - trace - DEBUG - send_request_body.started request=<Request [b'POST']>
2025-04-28 16:44:13,586 - [Worker-7] - _trace.py:47 - trace - DEBUG - send_request_body.complete
2025-04-28 16:44:13,586 - [Worker-7] - _trace.py:47 - trace - DEBUG - receive_response_headers.started request=<Request [b'POST']>
2025-04-28 16:44:15,156 - [Worker-7] - _trace.py:47 - trace - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 400, b'Bad Request', [(b'Date', b'Mon, 28 Apr 2025 16:44:14 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'205'), (b'Connection', b'keep-alive'), (b'access-control-expose-headers', b'X-Request-ID'), (b'openai-organization', b'user-ub6kcjjgjcqflrzwnh3ekrmh'), (b'openai-processing-ms', b'13'), (b'openai-version', b'2020-10-01'), (b'x-ratelimit-limit-requests', b'10000'), (b'x-ratelimit-limit-tokens', b'200000'), (b'x-ratelimit-remaining-requests', b'9999'), (b'x-ratelimit-remaining-tokens', b'199572'), (b'x-ratelimit-reset-requests', b'8.64s'), (b'x-ratelimit-reset-tokens', b'128ms'), (b'x-request-id', b'req_3677e52e7a964e37b8e0c5aadf2608ec'), (b'strict-transport-security', b'max-age=31536000; includeSubDomains; preload'), (b'cf-cache-status', b'DYNAMIC'), (b'Set-Cookie', b'__cf_bm=pX4W5t7_XNbHyYES9IGAC2GBnfE0MnAmlkTraveYLtE-1745858654-1.0.1.1-2ezGsC0sFWIJ3qiYsv1cM6Aeg.GFVaogvbb6Ghm_5.tXUVddftU3QSZOWhJYt14Ih8vN9V1lRsLIJDQygPOuhw9N_8u6mqkgpzakP_oBVrM; path=/; expires=Mon, 28-Apr-25 17:14:14 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None'), (b'X-Content-Type-Options', b'nosniff'), (b'Set-Cookie', b'_cfuvid=POnR3lZ4TFeGeYyod0WBOdkRVS2FODfickNKRxJdNUA-1745858654986-0.0.1.1-604800000; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None'), (b'Server', b'cloudflare'), (b'CF-RAY', b'937805e7ef4292b8-CPH'), (b'alt-svc', b'h3=":443"; ma=86400')])
2025-04-28 16:44:15,161 - [Worker-7] - _client.py:1038 - _send_single_request - INFO - HTTP Request: POST https://api.openai.com/v1/audio/speech "HTTP/1.1 400 Bad Request"
2025-04-28 16:44:15,162 - [Worker-7] - _trace.py:47 - trace - DEBUG - receive_response_body.started request=<Request [b'POST']>
2025-04-28 16:44:15,162 - [Worker-7] - _trace.py:47 - trace - DEBUG - receive_response_body.complete
2025-04-28 16:44:15,163 - [Worker-7] - _trace.py:47 - trace - DEBUG - response_closed.started
2025-04-28 16:44:15,163 - [Worker-7] - _trace.py:47 - trace - DEBUG - response_closed.complete
2025-04-28 16:44:15,164 - [Worker-7] - _base_client.py:991 - _request - DEBUG - HTTP Response: POST https://api.openai.com/v1/audio/speech "400 Bad Request" Headers([('date', 'Mon, 28 Apr 2025 16:44:14 GMT'), ('content-type', 'application/json'), ('content-length', '205'), ('connection', 'keep-alive'), ('access-control-expose-headers', 'X-Request-ID'), ('openai-organization', 'user-ub6kcjjgjcqflrzwnh3ekrmh'), ('openai-processing-ms', '13'), ('openai-version', '2020-10-01'), ('x-ratelimit-limit-requests', '10000'), ('x-ratelimit-limit-tokens', '200000'), ('x-ratelimit-remaining-requests', '9999'), ('x-ratelimit-remaining-tokens', '199572'), ('x-ratelimit-reset-requests', '8.64s'), ('x-ratelimit-reset-tokens', '128ms'), ('x-request-id', 'req_3677e52e7a964e37b8e0c5aadf2608ec'), ('strict-transport-security', 'max-age=31536000; includeSubDomains; preload'), ('cf-cache-status', 'DYNAMIC'), ('set-cookie', '__cf_bm=pX4W5t7_XNbHyYES9IGAC2GBnfE0MnAmlkTraveYLtE-1745858654-1.0.1.1-2ezGsC0sFWIJ3qiYsv1cM6Aeg.GFVaogvbb6Ghm_5.tXUVddftU3QSZOWhJYt14Ih8vN9V1lRsLIJDQygPOuhw9N_8u6mqkgpzakP_oBVrM; path=/; expires=Mon, 28-Apr-25 17:14:14 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None'), ('x-content-type-options', 'nosniff'), ('set-cookie', '_cfuvid=POnR3lZ4TFeGeYyod0WBOdkRVS2FODfickNKRxJdNUA-1745858654986-0.0.1.1-604800000; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None'), ('server', 'cloudflare'), ('cf-ray', '937805e7ef4292b8-CPH'), ('alt-svc', 'h3=":443"; ma=86400')])
2025-04-28 16:44:15,164 - [Worker-7] - _base_client.py:999 - _request - DEBUG - request_id: req_3677e52e7a964e37b8e0c5aadf2608ec
2025-04-28 16:44:15,164 - [Worker-7] - _base_client.py:1004 - _request - DEBUG - Encountered httpx.HTTPStatusError
Traceback (most recent call last):
  File "/usr/local/lib/python3.11/site-packages/openai/_base_client.py", line 1002, in _request
    response.raise_for_status()
  File "/usr/local/lib/python3.11/site-packages/httpx/_models.py", line 763, in raise_for_status
    raise HTTPStatusError(message, request=request, response=self)
httpx.HTTPStatusError: Client error '400 Bad Request' for url 'https://api.openai.com/v1/audio/speech'
For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/400
2025-04-28 16:44:15,175 - [Worker-7] - _base_client.py:743 - _should_retry - DEBUG - Not retrying
2025-04-28 16:44:15,176 - [Worker-7] - _base_client.py:1022 - _request - DEBUG - Re-raising status error
2025-04-28 16:44:15,179 - [Worker-7] - audiobook_generator.py:87 - process_chapter - ERROR - Error processing chapter 1, error: Error code: 400 - {'error': {'message': "Invalid type for 'instructions': expected a string, but got null instead.", 'type': 'invalid_request_error', 'param': 'instructions', 'code': 'invalid_type'}}
Traceback (most recent call last):
  File "/app_src/audiobook_generator/core/audiobook_generator.py", line 81, in process_chapter
    tts_provider.text_to_speech(text, output_file, audio_tags)
  File "/app_src/audiobook_generator/tts_providers/openai_tts_provider.py", line 78, in text_to_speech
    response = self.client.audio.speech.create(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/resources/audio/speech.py", line 100, in create
    return self._post(
           ^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/_base_client.py", line 1242, in post
    return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/_base_client.py", line 919, in request
    return self._request(
           ^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/openai/_base_client.py", line 1023, in _request
    raise self._make_status_error_from_response(err.response) from None
openai.BadRequestError: Error code: 400 - {'error': {'message': "Invalid type for 'instructions': expected a string, but got null instead.", 'type': 'invalid_request_error', 'param': 'instructions', 'code': 'invalid_type'}}
2025-04-28 16:44:15,190 - audiobook_generator.py:171 - run - WARNING - The following chapters failed to convert:
2025-04-28 16:44:15,190 - audiobook_generator.py:173 - run - WARNING -   - Chapter 1: A chap name
2025-04-28 16:44:15,190 - audiobook_generator.py:174 - run - INFO - Conversion completed with 1 failed chapters.