Files
hyperframes/skills/media-use/audio/scripts/lyria-recipe.py
T
Miguel Ángel f8a1e2d315 fix(skills): pin UTF-8 in Python scripts instead of the platform code page (#3298)
Windows sizes Python's stdio and text-mode file IO to the ANSI code page
(cp1252), not UTF-8. Every skill Python script relied on that default:

  * analyze-beatgrid.py --print writes the glyphs cp1252 has no slot for
    (delta, arrow), so the brief died with UnicodeEncodeError on every Windows
    run — the reported crash;
  * its audiomap write_text() pairs ensure_ascii=False with the default file
    encoding, so a non-ASCII payload is unwritable there too;
  * lint_source.py read_text() raises UnicodeDecodeError before any rule runs
    when a Remotion source carries an em dash or a curly quote;
  * gen-stroke-path.py reads an SVG font whose glyph keys ARE literal
    characters, so a mis-decoded key stops matching the requested text.

Stdio is reconfigured to UTF-8 at import and every text-mode IO call names its
encoding. `errors` is carried across the reconfigure: it resets to "strict",
and CPython gives stderr "backslashreplace" on purpose so the diagnostic path
can never itself raise.

extract-audio-data.py also decoded ffmpeg's stderr strictly while reporting a
failure, which would bury the very error being reported on a Windows ffmpeg.

skills/python-encoding.test.mjs guards the class: it fails if any skill Python
script drops the stdio block or omits encoding= on a text-mode IO call. The
mode is read as a whole comma-delimited argument of mode characters only, so a
payload key like {"bpm": 120} cannot spell the check away.

Verified with a cp1252 stdio stream installed before module load, matching how
Windows starts the interpreter: pre-fix UnicodeEncodeError, post-fix both
glyphs present in the UTF-8 bytes. Not run on real Windows hardware.
2026-08-17 21:44:08 -04:00

137 lines
4.9 KiB
Python

#!/usr/bin/env python3
"""Generate BGM using Google Lyria RealTime API.
Usage:
python lyria-recipe.py --output <path> --duration <seconds> [tuning flags]
Requires:
$GOOGLE_API_KEY or $GEMINI_API_KEY environment variable (treated as aliases).
pip install google-genai python-dotenv. audio.mjs Step 4b installs these on
demand when a key is set but google.genai is not importable; if that install
fails it falls back to local MusicGen rather than leaving the video with no BGM.
"""
from __future__ import annotations
import argparse
import asyncio
import os
import sys
import wave
from pathlib import Path
# Windows sizes stdio to the ANSI code page (cp1252). These scripts emit UTF-8 on
# every platform; say so rather than depending on the console's code page. Carry
# `errors` across: reconfigure() resets it to "strict", and CPython deliberately gives
# stderr "backslashreplace" so the diagnostic path can never itself raise.
for _stream in (sys.stdout, sys.stderr):
if hasattr(_stream, "reconfigure"):
_stream.reconfigure(encoding="utf-8", errors=_stream.errors)
DEFAULT_PROMPT = "Uplifting corporate tech, bright and modern, gentle piano with synth pads"
SAMPLE_RATE = 48000
CHANNELS = 2
SAMPLE_WIDTH = 2 # 16-bit
def parse_args() -> argparse.Namespace:
p = argparse.ArgumentParser(description="Generate BGM via Google Lyria RealTime.")
p.add_argument("--output", required=True, help="Output WAV path.")
p.add_argument("--duration", type=float, required=True, help="Target duration in seconds.")
p.add_argument("--prompt", default=DEFAULT_PROMPT, help="Mood / instrumentation prompt.")
p.add_argument("--negative-prompt", default=None, help="Styles to exclude (optional).")
p.add_argument("--bpm", type=int, default=110)
p.add_argument("--brightness", type=float, default=0.8, help="0-1, higher = brighter mood.")
p.add_argument("--density", type=float, default=0.5, help="0-1, higher = fuller mix.")
p.add_argument(
"--scale",
default="MAJOR",
help="MAJOR / MINOR / PENTATONIC / etc. — see google.genai.types.Scale. Pass empty string for none.",
)
return p.parse_args()
async def generate_bgm(args: argparse.Namespace) -> dict:
from google import genai
from google.genai import types
api_key = os.environ.get("GOOGLE_API_KEY") or os.environ.get("GEMINI_API_KEY") or ""
if not api_key:
raise RuntimeError("Neither GOOGLE_API_KEY nor GEMINI_API_KEY is set.")
client = genai.Client(
api_key=api_key,
http_options={"api_version": "v1alpha"},
)
out_path = Path(args.output)
out_path.parent.mkdir(parents=True, exist_ok=True)
target_bytes = int(args.duration * SAMPLE_RATE * CHANNELS * SAMPLE_WIDTH)
cfg: dict = {"bpm": args.bpm, "temperature": 1.0}
if args.density is not None:
cfg["density"] = args.density
if args.brightness is not None:
cfg["brightness"] = args.brightness
if args.scale:
scale_enum = getattr(types.Scale, args.scale, None)
if scale_enum:
cfg["scale"] = scale_enum
prompts = [types.WeightedPrompt(text=args.prompt, weight=1.0)]
if args.negative_prompt:
prompts.append(types.WeightedPrompt(text=args.negative_prompt, weight=-1.0))
buf = bytearray()
timeout = args.duration + 8
async with client.aio.live.music.connect(
model="models/lyria-realtime-exp",
) as session:
await session.set_weighted_prompts(prompts=prompts)
await session.set_music_generation_config(
config=types.LiveMusicGenerationConfig(**cfg),
)
await session.play()
async def collect():
while len(buf) < target_bytes:
async for msg in session.receive():
sc = msg.server_content
if sc and sc.audio_chunks:
for chunk in sc.audio_chunks:
buf.extend(chunk.data)
if len(buf) >= target_bytes:
return
await asyncio.sleep(1e-6)
try:
await asyncio.wait_for(collect(), timeout=timeout)
except TimeoutError:
print(f"Timeout after {timeout:.0f}s, collected {len(buf)} bytes", file=sys.stderr)
audio = bytes(buf[:target_bytes])
with wave.open(str(out_path), "wb") as wf:
wf.setnchannels(CHANNELS)
wf.setsampwidth(SAMPLE_WIDTH)
wf.setframerate(SAMPLE_RATE)
wf.writeframes(audio)
actual_duration = len(audio) / (SAMPLE_RATE * CHANNELS * SAMPLE_WIDTH)
print(f"BGM: {out_path} ({actual_duration:.2f}s)")
return {"file": str(out_path), "duration_sec": round(actual_duration, 2)}
def main() -> None:
args = parse_args()
try:
asyncio.run(generate_bgm(args))
except RuntimeError as exc:
print(f"BGM generation failed: {exc}", file=sys.stderr)
sys.exit(1)
if __name__ == "__main__":
main()