#!/bin/sh
# Old Tam's voice (tools/voice/make_voice.py). Run after changing any line in
# data/tutorial.json or data/hints.json:
#
#   tools/voice/make_voice.sh          # just the lines that changed
#   tools/voice/make_voice.sh --all    # every line again
#
# Needs an Apple-silicon Mac (MLX), ffmpeg and uv. The first run sets up a
# Python 3.12 environment in tools/voice/.venv-qwen and downloads the models
# from Hugging Face: Qwen3-TTS 1.7B Base (about 4 GB) and Whisper large-v3
# turbo (about 1.6 GB), to check what each take says.

cd "$(dirname "$0")/../.." || exit 1
V=tools/voice/.venv-qwen
command -v ffmpeg >/dev/null || { echo "needs ffmpeg (brew install ffmpeg)"; exit 1; }
if [ ! -x "$V/bin/python" ]; then
	command -v uv >/dev/null || { echo "needs uv (https://docs.astral.sh/uv/)"; exit 1; }
	uv venv -q --python 3.12 "$V" || exit 1
	uv pip install -q --python "$V/bin/python" "mlx-audio==0.6.4" "mlx==0.32.4" "mlx-whisper==0.4.3" \
		"soundfile==0.13.1" "numpy==2.5.4" "transformers==5.22.2" || exit 1
fi
exec "$V/bin/python" tools/voice/make_voice.py "$@"