2026-05-19-00-11-40 新增Ubuntu配音工作流
This commit is contained in:
38
Tools_scripts_XunFei-Ubuntu/README.md
Normal file
38
Tools_scripts_XunFei-Ubuntu/README.md
Normal file
@@ -0,0 +1,38 @@
|
||||
# Tools_scripts_XunFei-Ubuntu
|
||||
|
||||
Ubuntu 版配音工具,使用 Bash + Python + ffmpeg 替代 PowerShell。
|
||||
|
||||
## Install
|
||||
|
||||
```bash
|
||||
sudo apt update
|
||||
sudo apt install -y python3 python3-pip ffmpeg
|
||||
python3 -m pip install -r Tools_scripts_XunFei-Ubuntu/requirements-ubuntu.txt
|
||||
```
|
||||
|
||||
## Environment
|
||||
|
||||
```bash
|
||||
export XF_APPID="your_app_id"
|
||||
export XF_APIKEY="your_api_key"
|
||||
export XF_APISECRET="your_api_secret"
|
||||
```
|
||||
|
||||
## Generate Voice
|
||||
|
||||
```bash
|
||||
./Tools_scripts_XunFei-Ubuntu/synthesize_xfyun_super_tts.sh \
|
||||
--script 配音稿.md \
|
||||
--output-dir 02_audio/super_tts \
|
||||
--voice x5_lingfeiyi_flow \
|
||||
--speed 50
|
||||
```
|
||||
|
||||
## Build Final Video
|
||||
|
||||
```bash
|
||||
python3 Tools_scripts_XunFei-Ubuntu/build_final_video_ubuntu.py \
|
||||
--video input.mp4 \
|
||||
--audio-dir 02_audio/super_tts \
|
||||
--output 05_outputs/final_voiceover.mp4
|
||||
```
|
||||
232
Tools_scripts_XunFei-Ubuntu/build_final_video_ubuntu.py
Executable file
232
Tools_scripts_XunFei-Ubuntu/build_final_video_ubuntu.py
Executable file
@@ -0,0 +1,232 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Build a final voice-over video on Ubuntu with ffmpeg."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import shutil
|
||||
import subprocess
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
AUDIO_EXTS = {".mp3", ".wav", ".m4a", ".aac", ".flac", ".ogg"}
|
||||
|
||||
|
||||
def run(cmd: list[str]) -> None:
|
||||
print("+ " + " ".join(cmd))
|
||||
subprocess.run(cmd, check=True)
|
||||
|
||||
|
||||
def require_tool(name: str) -> str:
|
||||
path = shutil.which(name)
|
||||
if not path:
|
||||
raise SystemExit(f"{name} is required. Install it with: sudo apt install -y ffmpeg")
|
||||
return path
|
||||
|
||||
|
||||
def media_duration(path: Path) -> float:
|
||||
result = subprocess.check_output(
|
||||
[
|
||||
"ffprobe",
|
||||
"-v",
|
||||
"error",
|
||||
"-show_entries",
|
||||
"format=duration",
|
||||
"-of",
|
||||
"default=nw=1:nk=1",
|
||||
str(path),
|
||||
],
|
||||
text=True,
|
||||
).strip()
|
||||
return float(result)
|
||||
|
||||
|
||||
def audio_files(audio_dir: Path) -> list[Path]:
|
||||
files = [
|
||||
path
|
||||
for path in sorted(audio_dir.iterdir())
|
||||
if path.is_file() and path.suffix.lower() in AUDIO_EXTS
|
||||
]
|
||||
if not files:
|
||||
raise FileNotFoundError(f"No audio files found in {audio_dir}")
|
||||
return files
|
||||
|
||||
|
||||
def concat_audio_dir(audio_dir: Path, work_dir: Path, silence: float) -> Path:
|
||||
work_dir.mkdir(parents=True, exist_ok=True)
|
||||
normalized: list[Path] = []
|
||||
silence_path = work_dir / "silence.wav"
|
||||
run(
|
||||
[
|
||||
"ffmpeg",
|
||||
"-hide_banner",
|
||||
"-loglevel",
|
||||
"error",
|
||||
"-y",
|
||||
"-f",
|
||||
"lavfi",
|
||||
"-t",
|
||||
f"{silence:.3f}",
|
||||
"-i",
|
||||
"anullsrc=channel_layout=stereo:sample_rate=48000",
|
||||
"-c:a",
|
||||
"pcm_s16le",
|
||||
str(silence_path),
|
||||
]
|
||||
)
|
||||
|
||||
for index, src in enumerate(audio_files(audio_dir), start=1):
|
||||
dst = work_dir / f"audio_{index:02d}.wav"
|
||||
run(
|
||||
[
|
||||
"ffmpeg",
|
||||
"-hide_banner",
|
||||
"-loglevel",
|
||||
"error",
|
||||
"-y",
|
||||
"-i",
|
||||
str(src),
|
||||
"-vn",
|
||||
"-ar",
|
||||
"48000",
|
||||
"-ac",
|
||||
"2",
|
||||
"-c:a",
|
||||
"pcm_s16le",
|
||||
str(dst),
|
||||
]
|
||||
)
|
||||
normalized.append(dst)
|
||||
|
||||
concat_items: list[Path] = []
|
||||
for index, item in enumerate(normalized):
|
||||
concat_items.append(item)
|
||||
if index != len(normalized) - 1 and silence > 0:
|
||||
concat_items.append(silence_path)
|
||||
|
||||
list_path = work_dir / "audio_concat.txt"
|
||||
with list_path.open("w", encoding="utf-8") as handle:
|
||||
for item in concat_items:
|
||||
escaped = item.resolve().as_posix().replace("'", "'\\''")
|
||||
handle.write(f"file '{escaped}'\n")
|
||||
|
||||
out_audio = work_dir / "combined_voice.wav"
|
||||
run(
|
||||
[
|
||||
"ffmpeg",
|
||||
"-hide_banner",
|
||||
"-loglevel",
|
||||
"error",
|
||||
"-y",
|
||||
"-f",
|
||||
"concat",
|
||||
"-safe",
|
||||
"0",
|
||||
"-i",
|
||||
str(list_path),
|
||||
"-c:a",
|
||||
"pcm_s16le",
|
||||
str(out_audio),
|
||||
]
|
||||
)
|
||||
return out_audio
|
||||
|
||||
|
||||
def parse_args() -> argparse.Namespace:
|
||||
parser = argparse.ArgumentParser(description="Combine one video with voice-over audio.")
|
||||
parser.add_argument("--video", type=Path, required=True, help="Source video path.")
|
||||
parser.add_argument("--audio", type=Path, default=None, help="Single voice-over audio file.")
|
||||
parser.add_argument("--audio-dir", type=Path, default=None, help="Directory of ordered audio files.")
|
||||
parser.add_argument("--output", type=Path, default=Path("05_outputs/final_voiceover.mp4"))
|
||||
parser.add_argument("--work-dir", type=Path, default=Path("04_intermediate/ubuntu_voiceover"))
|
||||
parser.add_argument("--silence", type=float, default=0.35, help="Gap seconds between audio files.")
|
||||
parser.add_argument("--width", type=int, default=1920)
|
||||
parser.add_argument("--height", type=int, default=1080)
|
||||
parser.add_argument("--fps", type=int, default=30)
|
||||
parser.add_argument("--crf", type=int, default=20)
|
||||
parser.add_argument("--preset", default="medium")
|
||||
parser.add_argument("--video-speed", type=float, default=None, help="Override automatic speed.")
|
||||
return parser.parse_args()
|
||||
|
||||
|
||||
def main() -> int:
|
||||
args = parse_args()
|
||||
require_tool("ffmpeg")
|
||||
require_tool("ffprobe")
|
||||
|
||||
if not args.video.exists():
|
||||
raise FileNotFoundError(args.video)
|
||||
if bool(args.audio) == bool(args.audio_dir):
|
||||
raise SystemExit("Use exactly one of --audio or --audio-dir.")
|
||||
|
||||
args.work_dir.mkdir(parents=True, exist_ok=True)
|
||||
args.output.parent.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
audio_path = args.audio if args.audio else concat_audio_dir(args.audio_dir, args.work_dir, args.silence)
|
||||
if not audio_path or not audio_path.exists():
|
||||
raise FileNotFoundError(audio_path)
|
||||
|
||||
video_duration = media_duration(args.video)
|
||||
audio_duration = media_duration(audio_path)
|
||||
if video_duration <= 0 or audio_duration <= 0:
|
||||
raise RuntimeError("Invalid media duration.")
|
||||
|
||||
speed = args.video_speed if args.video_speed else video_duration / audio_duration
|
||||
if speed <= 0:
|
||||
raise ValueError("--video-speed must be greater than 0.")
|
||||
|
||||
print(f"video_duration={video_duration:.3f}s")
|
||||
print(f"audio_duration={audio_duration:.3f}s")
|
||||
print(f"video_speed={speed:.6f}x")
|
||||
|
||||
vf = (
|
||||
f"[0:v]setpts=PTS/{speed:.8f},fps={args.fps},"
|
||||
f"scale={args.width}:{args.height}:force_original_aspect_ratio=decrease,"
|
||||
f"pad={args.width}:{args.height}:(ow-iw)/2:(oh-ih)/2:black,"
|
||||
"setsar=1,format=yuv420p[v];"
|
||||
"[1:a]aresample=48000,apad[a]"
|
||||
)
|
||||
run(
|
||||
[
|
||||
"ffmpeg",
|
||||
"-hide_banner",
|
||||
"-y",
|
||||
"-i",
|
||||
str(args.video),
|
||||
"-i",
|
||||
str(audio_path),
|
||||
"-filter_complex",
|
||||
vf,
|
||||
"-map",
|
||||
"[v]",
|
||||
"-map",
|
||||
"[a]",
|
||||
"-t",
|
||||
f"{audio_duration:.3f}",
|
||||
"-c:v",
|
||||
"libx264",
|
||||
"-preset",
|
||||
args.preset,
|
||||
"-crf",
|
||||
str(args.crf),
|
||||
"-c:a",
|
||||
"aac",
|
||||
"-b:a",
|
||||
"192k",
|
||||
"-ar",
|
||||
"48000",
|
||||
"-ac",
|
||||
"2",
|
||||
"-movflags",
|
||||
"+faststart",
|
||||
str(args.output),
|
||||
]
|
||||
)
|
||||
final_duration = media_duration(args.output)
|
||||
print(f"output={args.output}")
|
||||
print(f"final_duration={final_duration:.3f}s")
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
21
Tools_scripts_XunFei-Ubuntu/check_audio_duration.sh
Executable file
21
Tools_scripts_XunFei-Ubuntu/check_audio_duration.sh
Executable file
@@ -0,0 +1,21 @@
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
|
||||
TARGET="${1:-02_audio}"
|
||||
|
||||
if ! command -v ffprobe >/dev/null 2>&1; then
|
||||
echo "ffprobe is required. Install it with: sudo apt install -y ffmpeg" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
if [[ ! -e "$TARGET" ]]; then
|
||||
echo "Path not found: $TARGET" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
find "$TARGET" -type f \( -iname '*.mp3' -o -iname '*.wav' -o -iname '*.m4a' \) -print0 |
|
||||
sort -z |
|
||||
while IFS= read -r -d '' file; do
|
||||
duration="$(ffprobe -v error -show_entries format=duration -of default=nw=1:nk=1 "$file")"
|
||||
printf '%8.3fs %s\n' "$duration" "$file"
|
||||
done
|
||||
1
Tools_scripts_XunFei-Ubuntu/requirements-ubuntu.txt
Normal file
1
Tools_scripts_XunFei-Ubuntu/requirements-ubuntu.txt
Normal file
@@ -0,0 +1 @@
|
||||
websocket-client>=1.8.0
|
||||
5
Tools_scripts_XunFei-Ubuntu/synthesize_xfyun_super_tts.sh
Executable file
5
Tools_scripts_XunFei-Ubuntu/synthesize_xfyun_super_tts.sh
Executable file
@@ -0,0 +1,5 @@
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
python3 "$SCRIPT_DIR/xfyun_tts_ubuntu.py" --mode super "$@"
|
||||
5
Tools_scripts_XunFei-Ubuntu/synthesize_xfyun_tts.sh
Executable file
5
Tools_scripts_XunFei-Ubuntu/synthesize_xfyun_tts.sh
Executable file
@@ -0,0 +1,5 @@
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
python3 "$SCRIPT_DIR/xfyun_tts_ubuntu.py" --mode normal "$@"
|
||||
356
Tools_scripts_XunFei-Ubuntu/xfyun_tts_ubuntu.py
Executable file
356
Tools_scripts_XunFei-Ubuntu/xfyun_tts_ubuntu.py
Executable file
@@ -0,0 +1,356 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Generate XFYUN TTS voice files on Ubuntu.
|
||||
|
||||
This script supports both the normal XFYUN online TTS endpoint and the
|
||||
super-realistic TTS endpoint used by the PowerShell workflow.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import base64
|
||||
import email.utils
|
||||
import hashlib
|
||||
import hmac
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import sys
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
from urllib.parse import quote, urlparse
|
||||
|
||||
|
||||
NORMAL_TTS_URL = "wss://tts-api.xfyun.cn/v2/tts"
|
||||
SUPER_TTS_URL = "wss://cbm01.cn-huabei-1.xf-yun.com/v1/private/mcd9m97e6"
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ScriptSegment:
|
||||
index: str
|
||||
title: str
|
||||
text: str
|
||||
|
||||
|
||||
def safe_filename(value: str) -> str:
|
||||
cleaned = re.sub(r'[\\/:*?"<>|]', "", value).strip()
|
||||
return cleaned or "segment"
|
||||
|
||||
|
||||
def find_default_script(cwd: Path) -> Path:
|
||||
candidates = sorted(cwd.glob("*.md"))
|
||||
preferred = [
|
||||
path
|
||||
for path in candidates
|
||||
if path.name.startswith("配音稿") or path.name.lower().startswith("voice")
|
||||
]
|
||||
fallback = [
|
||||
path
|
||||
for path in candidates
|
||||
if not path.name.startswith("配音生成工作流") and path.name.lower() != "readme.md"
|
||||
]
|
||||
selected = (preferred or fallback or candidates)
|
||||
if not selected:
|
||||
raise FileNotFoundError("Cannot find script Markdown file. Use --script to specify one.")
|
||||
return selected[0]
|
||||
|
||||
|
||||
def load_segments(script_path: Path) -> list[ScriptSegment]:
|
||||
content = script_path.read_text(encoding="utf-8-sig")
|
||||
pattern = re.compile(
|
||||
r"(?ms)^##\s+([1-9])\.\s+(.+?)\r?\n(.*?)(?=^##\s+[1-9]\.\s+|\Z)"
|
||||
)
|
||||
matches = pattern.findall(content)
|
||||
if not matches:
|
||||
raise ValueError("Cannot find sections like '## 1. title' in script Markdown.")
|
||||
|
||||
segments: list[ScriptSegment] = []
|
||||
metadata = re.compile(r"^(说明|时长|备注|镜头|画面|音色|语速|输出|提示)[::]")
|
||||
for index, title, body in matches:
|
||||
lines = []
|
||||
for raw_line in body.splitlines():
|
||||
line = raw_line.strip()
|
||||
if not line or line.startswith("#") or metadata.match(line):
|
||||
continue
|
||||
lines.append(line)
|
||||
text = "\n".join(lines).replace("\t", " ").strip()
|
||||
if not text:
|
||||
raise ValueError(f"Section {index} has no readable text.")
|
||||
segments.append(ScriptSegment(index=index, title=title.strip(), text=text))
|
||||
return segments
|
||||
|
||||
|
||||
def build_auth_url(request_url: str, api_key: str, api_secret: str) -> str:
|
||||
uri = urlparse(request_url)
|
||||
host_name = uri.hostname or ""
|
||||
path = uri.path or "/"
|
||||
date = email.utils.formatdate(usegmt=True)
|
||||
signature_origin = f"host: {host_name}\ndate: {date}\nGET {path} HTTP/1.1"
|
||||
digest = hmac.new(
|
||||
api_secret.encode("utf-8"),
|
||||
signature_origin.encode("utf-8"),
|
||||
hashlib.sha256,
|
||||
).digest()
|
||||
signature = base64.b64encode(digest).decode("ascii")
|
||||
authorization_origin = (
|
||||
f'api_key="{api_key}", algorithm="hmac-sha256", '
|
||||
f'headers="host date request-line", signature="{signature}"'
|
||||
)
|
||||
authorization = base64.b64encode(authorization_origin.encode("utf-8")).decode("ascii")
|
||||
return (
|
||||
f"{request_url}?authorization={quote(authorization)}"
|
||||
f"&date={quote(date)}&host={quote(host_name)}"
|
||||
)
|
||||
|
||||
|
||||
def require_websocket():
|
||||
try:
|
||||
import websocket # type: ignore
|
||||
except ImportError as exc:
|
||||
raise SystemExit(
|
||||
"Missing dependency: websocket-client. Install it with:\n"
|
||||
" python3 -m pip install -r Tools_scripts_XunFei-Ubuntu/requirements-ubuntu.txt"
|
||||
) from exc
|
||||
return websocket
|
||||
|
||||
|
||||
def recv_json(socket: Any) -> dict[str, Any]:
|
||||
message = socket.recv()
|
||||
if isinstance(message, bytes):
|
||||
message = message.decode("utf-8")
|
||||
return json.loads(message)
|
||||
|
||||
|
||||
def synthesize_normal(
|
||||
*,
|
||||
text: str,
|
||||
out_file: Path,
|
||||
app_id: str,
|
||||
api_key: str,
|
||||
api_secret: str,
|
||||
voice: str,
|
||||
speed: int,
|
||||
volume: int,
|
||||
pitch: int,
|
||||
) -> None:
|
||||
websocket = require_websocket()
|
||||
url = build_auth_url(NORMAL_TTS_URL, api_key, api_secret)
|
||||
socket = websocket.create_connection(url, timeout=30)
|
||||
audio = bytearray()
|
||||
try:
|
||||
payload = {
|
||||
"common": {"app_id": app_id},
|
||||
"business": {
|
||||
"aue": "lame",
|
||||
"sfl": 1,
|
||||
"auf": "audio/L16;rate=16000",
|
||||
"vcn": voice,
|
||||
"speed": speed,
|
||||
"volume": volume,
|
||||
"pitch": pitch,
|
||||
"bgs": 0,
|
||||
"tte": "UTF8",
|
||||
"reg": "2",
|
||||
"rdn": "0",
|
||||
},
|
||||
"data": {
|
||||
"status": 2,
|
||||
"text": base64.b64encode(text.encode("utf-8")).decode("ascii"),
|
||||
},
|
||||
}
|
||||
socket.send(json.dumps(payload, ensure_ascii=False, separators=(",", ":")))
|
||||
while True:
|
||||
response = recv_json(socket)
|
||||
if response.get("code", 0) != 0:
|
||||
raise RuntimeError(
|
||||
f"XFYUN normal TTS failed: code={response.get('code')}, "
|
||||
f"message={response.get('message')}"
|
||||
)
|
||||
data = response.get("data") or {}
|
||||
if data.get("audio"):
|
||||
audio.extend(base64.b64decode(data["audio"]))
|
||||
if data.get("status") == 2:
|
||||
break
|
||||
finally:
|
||||
socket.close()
|
||||
|
||||
if not audio:
|
||||
raise RuntimeError("No audio data returned by XFYUN normal TTS.")
|
||||
out_file.write_bytes(audio)
|
||||
|
||||
|
||||
def synthesize_super(
|
||||
*,
|
||||
text: str,
|
||||
out_file: Path,
|
||||
app_id: str,
|
||||
api_key: str,
|
||||
api_secret: str,
|
||||
voice: str,
|
||||
speed: int,
|
||||
volume: int,
|
||||
pitch: int,
|
||||
raw_text: bool,
|
||||
) -> None:
|
||||
websocket = require_websocket()
|
||||
url = build_auth_url(SUPER_TTS_URL, api_key, api_secret)
|
||||
socket = websocket.create_connection(url, timeout=30)
|
||||
audio = bytearray()
|
||||
request_text = text if raw_text else base64.b64encode(text.encode("utf-8")).decode("ascii")
|
||||
try:
|
||||
payload = {
|
||||
"header": {"app_id": app_id, "status": 2},
|
||||
"parameter": {
|
||||
"oral": {
|
||||
"oral_level": "mid",
|
||||
"spark_assist": 1,
|
||||
"remain": 1,
|
||||
},
|
||||
"tts": {
|
||||
"vcn": voice,
|
||||
"speed": speed,
|
||||
"volume": volume,
|
||||
"pitch": pitch,
|
||||
"bgs": 0,
|
||||
"reg": 0,
|
||||
"rdn": 0,
|
||||
"rhy": 0,
|
||||
"watermask": 0,
|
||||
"implicit_watermark": False,
|
||||
"audio": {
|
||||
"encoding": "lame",
|
||||
"sample_rate": 24000,
|
||||
"channels": 1,
|
||||
"bit_depth": 16,
|
||||
"frame_size": 0,
|
||||
},
|
||||
},
|
||||
},
|
||||
"payload": {
|
||||
"text": {
|
||||
"encoding": "utf8",
|
||||
"compress": "raw",
|
||||
"format": "plain",
|
||||
"status": 2,
|
||||
"seq": 0,
|
||||
"text": request_text,
|
||||
}
|
||||
},
|
||||
}
|
||||
socket.send(json.dumps(payload, ensure_ascii=False, separators=(",", ":")))
|
||||
while True:
|
||||
response = recv_json(socket)
|
||||
header = response.get("header") or {}
|
||||
if header and header.get("code", 0) != 0:
|
||||
raise RuntimeError(
|
||||
f"XFYUN super TTS failed: code={header.get('code')}, "
|
||||
f"message={header.get('message')}, sid={header.get('sid')}"
|
||||
)
|
||||
if response.get("code", 0) != 0:
|
||||
raise RuntimeError(
|
||||
f"XFYUN super TTS failed: code={response.get('code')}, "
|
||||
f"message={response.get('message')}"
|
||||
)
|
||||
payload_audio = ((response.get("payload") or {}).get("audio") or {})
|
||||
if payload_audio.get("audio"):
|
||||
audio.extend(base64.b64decode(payload_audio["audio"]))
|
||||
if header.get("status") == 2 or payload_audio.get("status") == 2:
|
||||
break
|
||||
finally:
|
||||
socket.close()
|
||||
|
||||
if not audio:
|
||||
raise RuntimeError("No audio data returned by XFYUN super TTS.")
|
||||
out_file.write_bytes(audio)
|
||||
|
||||
|
||||
def validate_range(name: str, value: int) -> None:
|
||||
if value < 0 or value > 100:
|
||||
raise ValueError(f"{name} must be between 0 and 100.")
|
||||
|
||||
|
||||
def parse_args() -> argparse.Namespace:
|
||||
parser = argparse.ArgumentParser(description="Generate XFYUN TTS audio on Ubuntu.")
|
||||
parser.add_argument("--script", type=Path, default=None, help="Markdown script path.")
|
||||
parser.add_argument("--output-dir", type=Path, default=Path("02_audio/xfyun_tts"))
|
||||
parser.add_argument("--mode", choices=["normal", "super"], default="super")
|
||||
parser.add_argument("--voice", default=None, help="XFYUN vcn voice name.")
|
||||
parser.add_argument("--speed", type=int, default=50)
|
||||
parser.add_argument("--volume", type=int, default=70)
|
||||
parser.add_argument("--pitch", type=int, default=50)
|
||||
parser.add_argument("--raw-text", action="store_true", help="Use raw text for super TTS.")
|
||||
parser.add_argument("--overwrite", action="store_true", help="Overwrite existing mp3 files.")
|
||||
parser.add_argument("--dry-run", action="store_true", help="Only parse script and print plan.")
|
||||
return parser.parse_args()
|
||||
|
||||
|
||||
def main() -> int:
|
||||
args = parse_args()
|
||||
validate_range("speed", args.speed)
|
||||
validate_range("volume", args.volume)
|
||||
validate_range("pitch", args.pitch)
|
||||
|
||||
script_path = args.script or find_default_script(Path.cwd())
|
||||
segments = load_segments(script_path)
|
||||
voice = args.voice or ("xiaoyan" if args.mode == "normal" else "x5_lingfeiyi_flow")
|
||||
|
||||
print(f"script={script_path}")
|
||||
print(f"mode={args.mode}")
|
||||
print(f"voice={voice}")
|
||||
print(f"segments={len(segments)}")
|
||||
for segment in segments:
|
||||
print(f" {segment.index}. {segment.title} ({len(segment.text)} chars)")
|
||||
|
||||
if args.dry_run:
|
||||
return 0
|
||||
|
||||
app_id = os.environ.get("XF_APPID")
|
||||
api_key = os.environ.get("XF_APIKEY")
|
||||
api_secret = os.environ.get("XF_APISECRET")
|
||||
if not app_id or not api_key or not api_secret:
|
||||
raise SystemExit("Please set XF_APPID, XF_APIKEY and XF_APISECRET first.")
|
||||
|
||||
args.output_dir.mkdir(parents=True, exist_ok=True)
|
||||
for segment in segments:
|
||||
out_file = args.output_dir / f"{segment.index}-{safe_filename(segment.title)}.mp3"
|
||||
if out_file.exists() and not args.overwrite:
|
||||
print(f"skip existing: {out_file}")
|
||||
continue
|
||||
print(f"synthesizing {segment.index}: {segment.title}")
|
||||
if args.mode == "normal":
|
||||
synthesize_normal(
|
||||
text=segment.text,
|
||||
out_file=out_file,
|
||||
app_id=app_id,
|
||||
api_key=api_key,
|
||||
api_secret=api_secret,
|
||||
voice=voice,
|
||||
speed=args.speed,
|
||||
volume=args.volume,
|
||||
pitch=args.pitch,
|
||||
)
|
||||
else:
|
||||
synthesize_super(
|
||||
text=segment.text,
|
||||
out_file=out_file,
|
||||
app_id=app_id,
|
||||
api_key=api_key,
|
||||
api_secret=api_secret,
|
||||
voice=voice,
|
||||
speed=args.speed,
|
||||
volume=args.volume,
|
||||
pitch=args.pitch,
|
||||
raw_text=args.raw_text,
|
||||
)
|
||||
print(f"generated: {out_file}")
|
||||
|
||||
print("all voice files generated")
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
try:
|
||||
raise SystemExit(main())
|
||||
except KeyboardInterrupt:
|
||||
raise SystemExit(130)
|
||||
31
工程分析/实现方案-2026-05-19-00-11-40.md
Normal file
31
工程分析/实现方案-2026-05-19-00-11-40.md
Normal file
@@ -0,0 +1,31 @@
|
||||
# 实现方案
|
||||
|
||||
开始时间:2026-05-19-00-11-40
|
||||
|
||||
## Ubuntu 工具目录
|
||||
|
||||
新增 `Tools_scripts_XunFei-Ubuntu/`:
|
||||
|
||||
- `requirements-ubuntu.txt`:Ubuntu 脚本所需 Python 依赖。
|
||||
- `xfyun_tts_ubuntu.py`:核心讯飞 TTS 脚本,支持普通 TTS 与超拟人 TTS。
|
||||
- `synthesize_xfyun_tts.sh`:普通 TTS Bash 包装入口。
|
||||
- `synthesize_xfyun_super_tts.sh`:超拟人 TTS Bash 包装入口。
|
||||
- `check_audio_duration.sh`:检查音频时长的小工具。
|
||||
- `build_final_video_ubuntu.py`:将单个视频与配音音频合成为最终视频,并根据配音时长自动调整画面速度。
|
||||
|
||||
## Ubuntu 工作流文档
|
||||
|
||||
新增 `配音生成工作流-Ubuntu-Agent.md`:
|
||||
|
||||
- 说明目录结构、依赖安装和环境变量配置。
|
||||
- 说明配音稿格式。
|
||||
- 给出普通 TTS、超拟人 TTS、音频时长检查、视频合成的命令示例。
|
||||
- 给出 Agent 执行清单和常见问题。
|
||||
|
||||
## 实现要点
|
||||
|
||||
- Python TTS 脚本通过 HMAC-SHA256 生成讯飞 WebSocket 鉴权 URL。
|
||||
- 配音稿解析兼容 `## 1.` 到 `## 4.` 分段格式。
|
||||
- `--dry-run` 可在无讯飞凭证时验证配音稿解析结果。
|
||||
- 视频合成脚本使用 `ffprobe` 计算视频与音频时长,并用 `setpts=PTS/speed` 让画面匹配旁白。
|
||||
- 输出视频使用 H.264/AAC、yuv420p、faststart,保证浏览器兼容。
|
||||
42
工程分析/测试方案-2026-05-19-00-11-40.md
Normal file
42
工程分析/测试方案-2026-05-19-00-11-40.md
Normal file
@@ -0,0 +1,42 @@
|
||||
# 测试方案
|
||||
|
||||
开始时间:2026-05-19-00-11-40
|
||||
|
||||
## 静态检查
|
||||
|
||||
- `python3 -m py_compile Tools_scripts_XunFei-Ubuntu/xfyun_tts_ubuntu.py Tools_scripts_XunFei-Ubuntu/build_final_video_ubuntu.py`
|
||||
- `bash -n Tools_scripts_XunFei-Ubuntu/synthesize_xfyun_tts.sh`
|
||||
- `bash -n Tools_scripts_XunFei-Ubuntu/synthesize_xfyun_super_tts.sh`
|
||||
- `bash -n Tools_scripts_XunFei-Ubuntu/check_audio_duration.sh`
|
||||
|
||||
执行结果:全部通过。
|
||||
|
||||
## 功能检查
|
||||
|
||||
- 使用临时 Markdown 配音稿运行 `xfyun_tts_ubuntu.py --dry-run`,确认能解析 4 段。
|
||||
- 使用 ffmpeg 生成临时测试视频与音频,运行 `build_final_video_ubuntu.py`,确认能输出 H.264/AAC 成片。
|
||||
- 用 `ffprobe` 检查测试成片时长、编码和音频流。
|
||||
|
||||
执行结果:
|
||||
|
||||
- `xfyun_tts_ubuntu.py --dry-run` 可解析 4 段配音稿。
|
||||
- 已安装并验证 `websocket-client=1.9.0`。
|
||||
- 无讯飞凭证时脚本会在解析配音稿后明确提示 `Please set XF_APPID, XF_APIKEY and XF_APISECRET first.` 并退出。
|
||||
- `build_final_video_ubuntu.py` 使用临时测试视频和两段测试音频生成成片成功。
|
||||
- 测试成片信息:H.264 视频、AAC 音频,320x180,约 2.55 秒。
|
||||
- `check_audio_duration.sh` 可列出测试音频时长。
|
||||
|
||||
## 仓库检查
|
||||
|
||||
- `git diff --check`
|
||||
- `git status --short`
|
||||
|
||||
执行结果:
|
||||
|
||||
- `git diff --check` 通过。
|
||||
- 待提交内容仅包含 Ubuntu 工具目录、Ubuntu 工作流文档和工程分析文档。
|
||||
|
||||
## 部署检查
|
||||
|
||||
- 本次主要新增文档和脚本,不改变 Web 服务逻辑。
|
||||
- 按既有流程重新执行 `docker compose -f docker_compose_huijutec.yaml up -d --build` 并检查健康接口。
|
||||
32
工程分析/经验记录.md
32
工程分析/经验记录.md
@@ -239,3 +239,35 @@ B. 产生问题原因:录屏展示节奏偏慢,而旁白文案按介绍视
|
||||
C. 解决问题方案:用 `ffprobe` 计算原视频和旁白时长,按 `85.636 / 64.272 = 1.332400` 对视频做轻度变速,原始音频静音并替换为新旁白,输出 H.264/AAC 兼容格式。
|
||||
|
||||
D. 后续如何避免问题:合成介绍视频时先确定旁白时长,再用可接受的变速范围调整画面;如果变速超过自然范围,应优先重新剪辑画面而不是强行加速。
|
||||
|
||||
## 2026-05-19-00-11-40 Ubuntu 配音工作流
|
||||
|
||||
### 1. PowerShell 配音脚本不能直接作为 Ubuntu 工作流
|
||||
|
||||
A. 具体问题:原有讯飞配音脚本是 PowerShell 版本,Ubuntu 环境直接执行门槛高,且命令示例不符合 Linux 用户习惯。
|
||||
|
||||
B. 产生问题原因:早期工作流面向 Windows/PowerShell,脚本入口、环境变量设置、路径写法和执行权限都与 Ubuntu 不同。
|
||||
|
||||
C. 解决问题方案:新增 `Tools_scripts_XunFei-Ubuntu`,用 Bash 包装入口和 Python WebSocket 客户端实现普通 TTS、超拟人 TTS、音频时长检查和视频合成;新增 `配音生成工作流-Ubuntu-Agent.md` 写明 Ubuntu 安装与执行步骤。
|
||||
|
||||
D. 后续如何避免问题:跨平台工作流应分开维护平台入口文档,不要只替换命令片段;至少要覆盖依赖安装、环境变量、执行权限和常见错误。
|
||||
|
||||
### 2. 无凭证环境下也需要可测试脚本
|
||||
|
||||
A. 具体问题:讯飞 TTS 真实请求需要 `XF_APPID`、`XF_APIKEY`、`XF_APISECRET`,没有凭证时无法验证配音稿解析和脚本基础逻辑。
|
||||
|
||||
B. 产生问题原因:TTS 网络请求和配音稿解析原本耦合在一起,缺少离线检查路径。
|
||||
|
||||
C. 解决问题方案:在 `xfyun_tts_ubuntu.py` 中加入 `--dry-run`,先解析配音稿并输出段落计划;只有真正合成时才检查讯飞凭证和发起 WebSocket 请求。
|
||||
|
||||
D. 后续如何避免问题:依赖外部账号、网络或付费接口的脚本都应提供 dry-run 或 validate 模式,方便在无凭证环境完成结构校验。
|
||||
|
||||
### 3. Ubuntu 视频合成需要避免编码兼容问题
|
||||
|
||||
A. 具体问题:不同来源的音频段可能编码、采样率和声道数不一致,直接 concat 容易失败或生成不可播放音轨。
|
||||
|
||||
B. 产生问题原因:ffmpeg concat demuxer 要求输入流参数一致,多段 TTS 音频不一定完全相同。
|
||||
|
||||
C. 解决问题方案:`build_final_video_ubuntu.py` 在合并音频目录时先把每段音频统一转为 48kHz 双声道 PCM WAV,再拼接并与视频合成,最终输出 H.264/AAC MP4。
|
||||
|
||||
D. 后续如何避免问题:多段音频拼接前先标准化采样率、声道和编码;最终成片统一使用 H.264/AAC/yuv420p/faststart。
|
||||
|
||||
29
工程分析/需求分析-2026-05-19-00-11-40.md
Normal file
29
工程分析/需求分析-2026-05-19-00-11-40.md
Normal file
@@ -0,0 +1,29 @@
|
||||
# 需求分析
|
||||
|
||||
开始时间:2026-05-19-00-11-40
|
||||
|
||||
## 用户需求
|
||||
|
||||
新建一套适用于 Ubuntu 的配音工具与工作流文档:
|
||||
|
||||
- `Tools_scripts_XunFei-Ubuntu`
|
||||
- `配音生成工作流-Ubuntu-Agent.md`
|
||||
|
||||
## 现状
|
||||
|
||||
- 现有 `待配音视频/Tools_scripts_XunFei` 目录中的脚本为 PowerShell 版本,主要适用于 Windows 或已安装 PowerShell 的环境。
|
||||
- 现有工作流文档以 PowerShell 命令为主,不适合 Ubuntu 直接照抄执行。
|
||||
- Ubuntu 环境更适合使用 Bash + Python + ffmpeg 的组合。
|
||||
|
||||
## 目标
|
||||
|
||||
- 提供 Ubuntu 可执行的讯飞普通 TTS 与超拟人 TTS 脚本。
|
||||
- 保留原工作流中的配音稿格式、声音选择、语速控制、音频时长检查与视频合成步骤。
|
||||
- 提供单视频换配音并自动按旁白调整画面速度的视频合成脚本。
|
||||
- 新文档明确依赖安装、环境变量配置、常用命令、测试方式和常见问题。
|
||||
|
||||
## 约束
|
||||
|
||||
- 不在脚本中写入任何讯飞密钥。
|
||||
- 通过 `XF_APPID`、`XF_APIKEY`、`XF_APISECRET` 环境变量读取凭证。
|
||||
- 生成音频和视频的输出目录由用户指定,避免覆盖已有结果。
|
||||
242
配音生成工作流-Ubuntu-Agent.md
Normal file
242
配音生成工作流-Ubuntu-Agent.md
Normal file
@@ -0,0 +1,242 @@
|
||||
# 配音生成工作流 Ubuntu Agent
|
||||
|
||||
本文档用于指导 Agent 在 Ubuntu 环境中使用 `Tools_scripts_XunFei-Ubuntu`,将配音稿文字转为讯飞配音音频,并与视频合成为最终介绍视频。
|
||||
|
||||
## 1. 目录约定
|
||||
|
||||
建议保持以下结构:
|
||||
|
||||
```text
|
||||
项目目录/
|
||||
配音稿.md
|
||||
Tools_scripts_XunFei-Ubuntu/
|
||||
requirements-ubuntu.txt
|
||||
xfyun_tts_ubuntu.py
|
||||
synthesize_xfyun_tts.sh
|
||||
synthesize_xfyun_super_tts.sh
|
||||
check_audio_duration.sh
|
||||
build_final_video_ubuntu.py
|
||||
```
|
||||
|
||||
其中:
|
||||
|
||||
- `xfyun_tts_ubuntu.py`:核心 Python 脚本,支持普通 TTS 和超拟人 TTS。
|
||||
- `synthesize_xfyun_tts.sh`:普通讯飞 TTS 入口,默认声音 `xiaoyan`。
|
||||
- `synthesize_xfyun_super_tts.sh`:讯飞超拟人 TTS 入口,默认声音 `x5_lingfeiyi_flow`。
|
||||
- `check_audio_duration.sh`:批量查看 mp3、wav、m4a 等音频时长。
|
||||
- `build_final_video_ubuntu.py`:将单个视频与配音音频合成为最终视频,并按旁白时长自动调整画面速度。
|
||||
|
||||
## 2. 安装依赖
|
||||
|
||||
```bash
|
||||
sudo apt update
|
||||
sudo apt install -y python3 python3-pip ffmpeg
|
||||
python3 -m pip install -r Tools_scripts_XunFei-Ubuntu/requirements-ubuntu.txt
|
||||
chmod +x Tools_scripts_XunFei-Ubuntu/*.sh Tools_scripts_XunFei-Ubuntu/*.py
|
||||
```
|
||||
|
||||
如果使用虚拟环境:
|
||||
|
||||
```bash
|
||||
python3 -m venv .venv-tts
|
||||
source .venv-tts/bin/activate
|
||||
python -m pip install -r Tools_scripts_XunFei-Ubuntu/requirements-ubuntu.txt
|
||||
```
|
||||
|
||||
## 3. 配置讯飞环境变量
|
||||
|
||||
```bash
|
||||
export XF_APPID="你的AppId"
|
||||
export XF_APIKEY="你的ApiKey"
|
||||
export XF_APISECRET="你的ApiSecret"
|
||||
```
|
||||
|
||||
如需长期生效,可以写入 `~/.bashrc`:
|
||||
|
||||
```bash
|
||||
cat >> ~/.bashrc <<'EOF'
|
||||
export XF_APPID="你的AppId"
|
||||
export XF_APIKEY="你的ApiKey"
|
||||
export XF_APISECRET="你的ApiSecret"
|
||||
EOF
|
||||
source ~/.bashrc
|
||||
```
|
||||
|
||||
脚本不会保存密钥,也不要把真实密钥写入仓库。
|
||||
|
||||
## 4. 配音稿格式
|
||||
|
||||
脚本识别 Markdown 中的分段标题:
|
||||
|
||||
```markdown
|
||||
## 1. 第一段标题
|
||||
第一段配音正文。
|
||||
|
||||
## 2. 第二段标题
|
||||
第二段配音正文。
|
||||
|
||||
## 3. 第三段标题
|
||||
第三段配音正文。
|
||||
|
||||
## 4. 第四段标题
|
||||
第四段配音正文。
|
||||
```
|
||||
|
||||
注意:
|
||||
|
||||
- 标题建议保持 `## 1.` 到 `## 4.`。
|
||||
- 输出文件名会使用段号和标题,例如 `1-第一段标题.mp3`。
|
||||
- `说明:`、`时长:`、`备注:`、`镜头:`、`画面:` 等元信息行会被忽略。
|
||||
- 正文只放最终朗读内容,不要放内部提示词。
|
||||
|
||||
可先做干跑检查:
|
||||
|
||||
```bash
|
||||
python3 Tools_scripts_XunFei-Ubuntu/xfyun_tts_ubuntu.py \
|
||||
--script 配音稿.md \
|
||||
--dry-run
|
||||
```
|
||||
|
||||
## 5. 普通 TTS 合成
|
||||
|
||||
普通 TTS 适合快速生成清晰稳定的中文配音。
|
||||
|
||||
```bash
|
||||
./Tools_scripts_XunFei-Ubuntu/synthesize_xfyun_tts.sh \
|
||||
--script 配音稿.md \
|
||||
--output-dir 02_audio/tts_audio_xiaoyan \
|
||||
--voice xiaoyan \
|
||||
--speed 50 \
|
||||
--volume 70 \
|
||||
--pitch 50
|
||||
```
|
||||
|
||||
## 6. 超拟人 TTS 合成
|
||||
|
||||
超拟人 TTS 更适合项目汇报、系统介绍和宣传片。
|
||||
|
||||
```bash
|
||||
./Tools_scripts_XunFei-Ubuntu/synthesize_xfyun_super_tts.sh \
|
||||
--script 配音稿.md \
|
||||
--output-dir 02_audio/super_tts_x5_lingfeiyi \
|
||||
--voice x5_lingfeiyi_flow \
|
||||
--speed 50 \
|
||||
--volume 70 \
|
||||
--pitch 50
|
||||
```
|
||||
|
||||
如果接口要求明文文本模式,可加:
|
||||
|
||||
```bash
|
||||
./Tools_scripts_XunFei-Ubuntu/synthesize_xfyun_super_tts.sh \
|
||||
--script 配音稿.md \
|
||||
--output-dir 02_audio/super_tts_raw \
|
||||
--raw-text
|
||||
```
|
||||
|
||||
## 7. 声音和语速选择
|
||||
|
||||
- `--voice`:讯飞发音人,也就是 `vcn`。
|
||||
- `--speed`:语速,通常 `0-100`,默认 `50`。
|
||||
- `--volume`:音量,通常 `0-100`,默认 `70`。
|
||||
- `--pitch`:音调,通常 `0-100`,默认 `50`。
|
||||
- `--overwrite`:覆盖已存在的音频文件。
|
||||
|
||||
建议:
|
||||
|
||||
- 系统介绍:优先用超拟人 TTS,例如 `x5_lingfeiyi_flow`。
|
||||
- 快速校稿:使用普通 TTS,例如 `xiaoyan`。
|
||||
- 需要缩短成片时长:先压缩文案,再把 `--speed` 调到 `55-60`。
|
||||
|
||||
## 8. 检查音频时长
|
||||
|
||||
```bash
|
||||
./Tools_scripts_XunFei-Ubuntu/check_audio_duration.sh 02_audio/super_tts_x5_lingfeiyi
|
||||
```
|
||||
|
||||
如果总时长过长:
|
||||
|
||||
- 优先删减配音稿。
|
||||
- 其次略微提高 `--speed`。
|
||||
- 最后再调整视频变速。
|
||||
|
||||
不建议为了追赶过长旁白而大幅加速视频,否则画面会不自然。
|
||||
|
||||
## 9. 合成最终视频
|
||||
|
||||
如果已有一个完整录屏和一组分段配音:
|
||||
|
||||
```bash
|
||||
python3 Tools_scripts_XunFei-Ubuntu/build_final_video_ubuntu.py \
|
||||
--video 待配音视频/ISISeg-介入导丝视频分割工作台-使用展示.mp4 \
|
||||
--audio-dir 02_audio/super_tts_x5_lingfeiyi \
|
||||
--output 05_outputs/ISISeg-系统使用视频-配音版.mp4
|
||||
```
|
||||
|
||||
如果已经有合并好的单个旁白音频:
|
||||
|
||||
```bash
|
||||
python3 Tools_scripts_XunFei-Ubuntu/build_final_video_ubuntu.py \
|
||||
--video input.mp4 \
|
||||
--audio voiceover.mp3 \
|
||||
--output 05_outputs/final_voiceover.mp4
|
||||
```
|
||||
|
||||
脚本会:
|
||||
|
||||
- 用 `ffprobe` 读取视频和旁白时长。
|
||||
- 自动计算画面变速系数。
|
||||
- 静音原视频音轨,只保留新旁白。
|
||||
- 输出 H.264/AAC、yuv420p、faststart MP4。
|
||||
|
||||
常用参数:
|
||||
|
||||
- `--width 1920 --height 1080`:输出分辨率。
|
||||
- `--fps 30`:输出帧率。
|
||||
- `--silence 0.35`:多段配音之间插入的静音秒数。
|
||||
- `--video-speed 1.25`:手动指定画面速度,覆盖自动计算。
|
||||
|
||||
## 10. Agent 执行清单
|
||||
|
||||
1. 确认 `Tools_scripts_XunFei-Ubuntu` 存在。
|
||||
2. 检查 `ffmpeg`、`ffprobe`、`python3` 是否可用。
|
||||
3. 安装 `requirements-ubuntu.txt` 中的依赖。
|
||||
4. 检查 `XF_APPID`、`XF_APIKEY`、`XF_APISECRET`。
|
||||
5. 创建或读取配音稿,并用 `--dry-run` 校验分段。
|
||||
6. 根据场景选择普通 TTS 或超拟人 TTS。
|
||||
7. 设置独立输出目录,避免覆盖不同声音和语速的试听结果。
|
||||
8. 生成音频后运行 `check_audio_duration.sh`。
|
||||
9. 用 `build_final_video_ubuntu.py` 合成最终视频。
|
||||
10. 用 `ffprobe` 检查最终视频时长、编码和音频流。
|
||||
|
||||
## 11. 常见问题
|
||||
|
||||
### Missing dependency: websocket-client
|
||||
|
||||
运行:
|
||||
|
||||
```bash
|
||||
python3 -m pip install -r Tools_scripts_XunFei-Ubuntu/requirements-ubuntu.txt
|
||||
```
|
||||
|
||||
### Please set XF_APPID, XF_APIKEY and XF_APISECRET first
|
||||
|
||||
说明当前终端没有讯飞凭证环境变量。设置后重新执行脚本:
|
||||
|
||||
```bash
|
||||
export XF_APPID="你的AppId"
|
||||
export XF_APIKEY="你的ApiKey"
|
||||
export XF_APISECRET="你的ApiSecret"
|
||||
```
|
||||
|
||||
### Cannot find script Markdown file
|
||||
|
||||
请使用 `--script 配音稿.md` 显式指定配音稿。
|
||||
|
||||
### ffmpeg 或 ffprobe 不存在
|
||||
|
||||
运行:
|
||||
|
||||
```bash
|
||||
sudo apt install -y ffmpeg
|
||||
```
|
||||
Reference in New Issue
Block a user