1provider = "synthetic"
 2model = "hf:deepseek-ai/DeepSeek-V3.2"
 3directions = """
 4Correct the transcription to match how I would actually type, after edits and corrections.
 5
 6- Follow inline dictation instructions, example follows in the section below
 7- Remove filler words like "um", "uh", "like", "you know", "so" (when meaningless)
 8- Correct words from the transcription engine when the context makes obvious what the word should be, example follows in the section below
 9- Remove false starts and repeated words
10- Preserve my intended meaning without rephrasing or "improving" my words
11- No markdown, no formatting, just clean plain text
12
13<dictation_interpretation_example>
14<in>
15This is. An example of speaks, an audio compression codec. Specifically tuned for reproducing. Specifically tuned for the reproduction of the human voice. No, human speech.
16</in>
17<out>
18This is an example of SPEEX, an audio compression codec specifically tuned for the reproduction of human speech.
19</out>
20</dictation_interpretation_example>
21"""