Organize repository: create scripts/ and docs/ directories

- Move utility scripts to scripts/ directory:
  - add_voice.py (add custom voices)
  - say.py (CLI TTS client)
  - test_voices.sh (voice testing)
  - download_samples.sh (OpenAI samples)

- Remove Windows batch files (.bat) - Linux/Docker focus
  - startup.bat
  - download_samples.bat
  - download_voices_tts-1.bat
  - download_voices_tts-1-hd.bat

- Create docs/ directory with AUDIT.md:
  - Complete repository file audit
  - Document 10+ abandoned TTS models to integrate
  - Plan for binary mirror strategy
  - Outline future refactoring to src/ structure

Raccoon mission: Scripts are in scripts/, docs reference them.
No code belongs in docs/ - only documentation.

🦝 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Russell Ballestrini 2025-11-09 09:25:21 -05:00
parent 91862d4f82
commit e8183b4585
9 changed files with 340 additions and 30 deletions

63
scripts/add_voice.py Executable file
View file

@ -0,0 +1,63 @@
#!/usr/bin/env python
import argparse
import os
import shutil
import yaml
print("!! WARNING EXPERIMENTAL !! - THIS TOOL WILL ERASE ALL COMMENTS FROM THE CONFIG FILES .. OR WORSE!!")
parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('sample', action='store', help="Set the wav sample file")
parser.add_argument('-n', '--name', action='store', help="Set the name for the voice (by default will use the WAV file name)")
parser.add_argument('-l', '--language', action='store', default="auto", help="Set the language for the voice",
choices=['auto', 'en', 'es', 'fr', 'de', 'it', 'pt', 'pl', 'tr', 'ru', 'nl', 'cs', 'ar', 'zh-cn', 'ja', 'hu', 'ko', 'hi'])
parser.add_argument('--openai-model', action='store', default="tts-1-hd", help="Set the openai model for the voice")
parser.add_argument('--xtts-model', action='store', default="xtts", help="Set the xtts model for the voice (if using a custom model, also set model_path)")
parser.add_argument('--model-path', action='store', default=None, help="Set the path for a custom xtts model")
parser.add_argument('--config-path', action='store', default="config/voice_to_speaker.yaml", help="Set the config file path")
parser.add_argument('--voice-path', action='store', default="voices", help="Set the default voices file path")
parser.add_argument('--default-path', action='store', default="voice_to_speaker.default.yaml", help="Set the default config file path")
args = parser.parse_args()
basename = os.path.basename(args.sample)
name_noext, ext = os.path.splitext(basename)
if not args.name:
args.name = name_noext
else:
basename = f"{args.name}.wav"
dest_file = os.path.join(args.voice_path, basename)
if args.sample != dest_file:
shutil.copy2(args.sample, dest_file)
if not os.path.exists(args.config_path):
shutil.copy2(args.default_path, args.config_path)
with open(args.config_path, 'r', encoding='utf8') as file:
voice_map = yaml.safe_load(file)
model_conf = voice_map.get(args.openai_model, {})
model_conf[args.name] = {
'model': args.xtts_model,
'speaker': os.path.join(args.voice_path, basename),
'language': args.language,
}
if args.model_path:
model_conf[args.name]['model_path'] = args.model_path
voice_map[args.openai_model] = model_conf
with open(args.config_path, 'w', encoding='utf8') as ofile:
yaml.safe_dump(voice_map, ofile, default_flow_style=False, allow_unicode=True)
print(f"Updated: {args.config_path}")
print(f"Added voice: {args.openai_model}/{args.name}")
print(f"Added section:")
print(f"{args.openai_model}:")
print(f" {args.name}:")
print(f" model: {model_conf[args.name]['model']}")
print(f" speaker: {model_conf[args.name]['speaker']}")
print(f" language: {model_conf[args.name]['language']}")

4
scripts/download_samples.sh Executable file
View file

@ -0,0 +1,4 @@
#!/bin/sh
for i in alloy echo fable onyx nova shimmer; do
[ ! -e "voices/$i.wav" ] && curl -s https://cdn.openai.com/API/docs/audio/$i.wav | ffmpeg -loglevel error -i - -ar 22050 -ac 1 voices/$i.wav
done

96
scripts/say.py Executable file
View file

@ -0,0 +1,96 @@
#!/usr/bin/env python
import sys
import os
import atexit
import tempfile
import argparse
try:
import dotenv
dotenv.load_dotenv(override=True)
except ImportError:
pass
try:
from playsound import playsound
except ImportError:
playsound = None
import openai
def parse_args(argv):
parser = argparse.ArgumentParser(
description='Text to speech using the OpenAI API',
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
)
parser.add_argument("-m", "--model", type=str, default="tts-1", help="The model to use")#, choices=["tts-1", "tts-1-hd"])
parser.add_argument("-v", "--voice", type=str, default="alloy", help="The voice of the speaker")#, choices=["alloy", "echo", "fable", "onyx", "nova", "shimmer"])
parser.add_argument("-f", "--format", type=str, default="mp3", choices=["mp3", "aac", "opus", "flac"], help="The output audio format")
parser.add_argument("-s", "--speed", type=float, default=1.0, help="playback speed, 0.25-4.0")
parser.add_argument("-t", "--text", type=str, default=None, help="Provide text to read on the command line")
parser.add_argument("-i", "--input", type=str, default=None, help="Read text from a file (default is to read from stdin)")
if playsound is None:
parser.add_argument("-o", "--output", type=str, help="The filename to save the output to") # required
parser.add_argument("-p", "--playsound", type=None, default=None, help="python playsound not found. pip install playsound")
else:
parser.add_argument("-o", "--output", type=str, default=None, help="The filename to save the output to") # not required
parser.add_argument("-p", "--playsound", action="store_true", help="Play the audio")
args = parser.parse_args(argv)
return args
if __name__ == "__main__":
args = parse_args(sys.argv[1:])
if args.playsound and playsound is None:
print("playsound module not found, audio will not be played, use -o <filename> to save output to a file. pip install playsound")
sys.exit(1)
if not args.playsound and not args.output:
print("Must select one of playsound (-p) or output file name (-o)")
sys.exit(1)
if args.input is None and args.text is None:
text = sys.stdin.read()
elif args.text:
text = args.text
elif args.input:
if os.path.exists(args.input):
with open(args.input, 'r') as f:
text = f.read()
else:
print(f"Warning! File not found: {args.input}\nFalling back to old behavior for -i")
text = args.input
client = openai.OpenAI(
# This part is not needed if you set these environment variables before import openai
# export OPENAI_API_KEY=sk-11111111111
# export OPENAI_BASE_URL=http://localhost:8000/v1
api_key = os.environ.get("OPENAI_API_KEY", "sk-ip"),
base_url = os.environ.get("OPENAI_BASE_URL", "http://localhost:8000/v1"),
)
if args.playsound and args.output is None:
_, args.output = tempfile.mkstemp(suffix='.wav')
def cleanup():
os.unlink(args.output)
atexit.register(cleanup)
with client.audio.speech.with_streaming_response.create(
model=args.model,
voice=args.voice,
speed=args.speed,
response_format=args.format,
input=text,
) as response:
response.stream_to_file(args.output)
if args.playsound:
playsound(args.output)

67
scripts/test_voices.sh Executable file
View file

@ -0,0 +1,67 @@
#!/bin/bash
URL=${1:-http://localhost:8000/v1/audio/speech}
curl -s $URL -H "Content-Type: application/json" -d "{
\"model\": \"tts-1\",
\"input\": \"I'm going to play you the original voice, followed by the piper voice and finally the X T T S version 2 voice\",
\"voice\": \"echo\",
\"speed\": 1.0
}" | mpv --really-quiet -
for voice in alloy echo fable onyx nova shimmer ; do
echo $voice
curl -s $URL -H "Content-Type: application/json" -d "{
\"model\": \"tts-1\",
\"input\": \"original\",
\"voice\": \"echo\",
\"speed\": 1.0
}" | mpv --really-quiet -
curl -s https://cdn.openai.com/API/docs/audio/$voice.wav | mpv --really-quiet -
curl -s $URL -H "Content-Type: application/json" -d "{
\"model\": \"tts-1\",
\"input\": \"The quick brown fox jumped over the lazy dog. This voice is called $voice, how do you like this voice?\",
\"voice\": \"$voice\",
\"speed\": 1.0
}" | mpv --really-quiet -
curl -s $URL -H "Content-Type: application/json" -d "{
\"model\": \"tts-1-hd\",
\"input\": \"The quick brown fox jumped over the lazy dog. This HD voice is called $voice, how do you like this voice?\",
\"voice\": \"$voice\",
\"speed\": 1.0
}" | mpv --really-quiet -
done
curl -s $URL -H "Content-Type: application/json" -d "{
\"model\": \"tts-1\",
\"input\": \"the slowest voice\",
\"voice\": \"onyx\",
\"speed\": 0.25
}" | mpv --really-quiet -
curl -s $URL -H "Content-Type: application/json" -d "{
\"model\": \"tts-1-hd\",
\"input\": \"the slowest HD voice\",
\"voice\": \"onyx\",
\"speed\": 0.25
}" | mpv --really-quiet -
curl -s $URL -H "Content-Type: application/json" -d "{
\"model\": \"tts-1\",
\"input\": \"And this is how fast it can go, the fastest voice\",
\"voice\": \"nova\",
\"speed\": 4.0
}" | mpv --really-quiet -
curl -s $URL -H "Content-Type: application/json" -d "{
\"model\": \"tts-1-hd\",
\"input\": \"And this is how fast it can go, the fastest HD voice\",
\"voice\": \"nova\",
\"speed\": 4.0
}" | mpv --really-quiet -