Comment by piotrrojek

If someone is interested, this is my supershort zsh/bash scripts that I keep in .zshrc for doing the same thing using plain whisper.cpp, ffmpeg and yt-dlp (`brew install whisper-cpp yt-dlp` for Mac); I output it in vtt format (subtitles) though, but it's easy enough to change it to txt.

  yt_to_srt() {
    local url="$1"
    local output_base="$2"
    local language="${3:-en}"

    yt-dlp -x --audio-format wav --postprocessor-args "-ar 16000" -o "$output_base.wav" "$url"
    whisper-cli --language "$language" --model "$WHISPER_MODEL" --split-on-word --max-len 65 --output-vtt --output-file "$output_base" --file "$output_base.wav"
    rm "$output_base.wav"
  }

  file_to_srt() {
    local filepath="$1"
    local language="${2:-en}"

    local filename=$(basename "$filepath")
    local filename_no_ext="${filename%.*}"
    local output_base="$filename_no_ext"
    local temp_wav="$output_base.wav"

    ffmpeg -i "$filepath" -vn -acodec pcm_s16le -ar 16000 -ac 1 "$temp_wav"
    whisper-cli --language "$language" --model "$WHISPER_MODEL" --split-on-word --max-len 65 --output-vtt --output-file "$output_base" --file "$temp_wav"
    rm "$temp_wav"
  }

plus additional bootstrap script for large-v3-turbo model from my chez-moi dotfiles:

  #!/bin/bash
  # Download whisper.cpp models from Hugging Face (runs once per machine).
  set -euo pipefail
  MODELS_DIR="$HOME/whisper-models"
  BASE_URL="https://huggingface.co/ggerganov/whisper.cpp/resolve/main"
  MODELS=("ggml-large-v3-turbo.bin" "ggml-tiny.bin")
  mkdir -p "$MODELS_DIR"
  for model in "${MODELS[@]}"; do
    if [ ! -f "$MODELS_DIR/$model" ]; then
      echo "Downloading $model..."
      curl -L --progress-bar -o "$MODELS_DIR/$model" "$BASE_URL/$model"
    else
      echo "$model already exists, skipping."
    fi
  done
  echo "Whisper models ready at $MODELS_DIR"