Fixes to get voice working properly, not fully confident it'll work under pressure but it's done well in small tests

bin/breadbot_common.py

@@ -169,11 +169,11 @@ def mix_audio_with_ffmpeg(files: list[TranscriptableFile], media_folder_path: st
 
     output_file_name = Path(
         media_folder_path,
-        call_id,
+        str(call_id),
         "output.mp3" if is_final_pass else "intermediate-" + "".join(random.choices(string.ascii_uppercase + string.digits, k=10)) + ".mp3"
     )
 
-    command_list.append(output_file_name)
+    command_list.append(str(output_file_name))
 
     # TODO shell = True isn't great, I don't remember the reason why it has to be this way
     # I *think* it had something to do with me not using ffmpeg's absolute path

bin/breadmixer.py

@@ -2,7 +2,7 @@ import json
 import os
 import copy
 from pathlib import Path
-from datetime import datetime
+from datetime import datetime, timezone
 from breadbot_common import SQLite, MySQL, TranscriptableFile, mix_audio_with_ffmpeg
 from txtai.pipeline import Transcription
 
@@ -36,20 +36,25 @@ transcriber = Transcription("openai/whisper-base")
 for call in calls_needing_work[1]:
     all_files = os.listdir(Path(
         config_json["media_voice_folder"],
-        call[0]
+        str(call[0])
     ))
 
     transcriptable_files = []
 
     for file in all_files:
+        print(file)
         file_name_no_extension = file.split('.')[0]
         timestamp = int(file_name_no_extension.split('-')[0])
         user_snowflake = file_name_no_extension.split('-')[1]
-        file_stamp_as_datetime = datetime.fromtimestamp(timestamp / 1000)
-        time_diff = file_stamp_as_datetime - call[1]
+        file_stamp_as_datetime = datetime.fromtimestamp(timestamp / 1000, timezone.utc)
+        print(file_stamp_as_datetime)
+        print(type(call[1]))
+        print(call[1])
+        time_diff = file_stamp_as_datetime - datetime.fromisoformat(call[1] + 'Z')
+        print(time_diff)
 
         transcriptable_files.append(TranscriptableFile(
-            file_path = file,
+            file_path = str(Path(config_json["media_voice_folder"], str(call[0]), file)),
             real_date = file_stamp_as_datetime,
             milliseconds_from_start = int((time_diff.seconds * 1000) + (time_diff.microseconds / 1000)),
             user_snowflake = user_snowflake
@@ -60,6 +65,11 @@ for call in calls_needing_work[1]:
     # TODO Possibly RAM abusive solution to wanting to keep the original list around
     ffmpeg_files = copy.deepcopy(transcriptable_files)
 
+    for file in ffmpeg_files:
+        print(file.file_path)
+        print(file.real_date)
+        print(file.milliseconds_from_start)
+
     # TODO Error handling for all ffmpeg operations
     while len(ffmpeg_files) > MAX_FILES_PER_CYCLE:
         ffmpeg_files = [
@@ -84,9 +94,9 @@ for call in calls_needing_work[1]:
         "compare": "="
     }])
 
-    for file in os.listdir(Path(config_json["media_voice_folder"], call[0])):
+    for file in os.listdir(Path(config_json["media_voice_folder"], str(call[0]))):
         if file.startswith("intermediate"):
-            os.remove(Path(config_json["media_voice_folder"], call[0], file))
+            os.remove(Path(config_json["media_voice_folder"], str(call[0]), file))
 
     for file in transcriptable_files:
         text = transcriber(file.file_path)