lostecho/edge-tts
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

More fixes

Browse Source
This commit is contained in:
rany
2021-06-05 18:20:20 +03:00
parent bc99f10b51
commit a29581479e
2 changed files with 11 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
setup.py
View File

@@ -16,7 +16,7 @@ with open("README.md", "r", encoding="utf-8") as fh:
setuptools.setup( setuptools.setup(
name="edge-tts", name="edge-tts",
version="0.0.1", version="0.0.2",
author="rany", author="rany",
author_email="ranygh@riseup.net", author_email="ranygh@riseup.net",
description="Microsoft Edge's TTS", description="Microsoft Edge's TTS",

19
src/edgeTTS/__init__.py
View File

@@ -18,9 +18,6 @@ trustedClientToken = '6A5AA1D4EAFF4E9FB37E23D68491D6F4'
wssUrl = 'wss://speech.platform.bing.com/consumer/speech/synthesize/readaloud/edge/v1?TrustedClientToken=' + trustedClientToken wssUrl = 'wss://speech.platform.bing.com/consumer/speech/synthesize/readaloud/edge/v1?TrustedClientToken=' + trustedClientToken
voiceList = 'https://speech.platform.bing.com/consumer/speech/synthesize/readaloud/voices/list?trustedclienttoken=' + trustedClientToken voiceList = 'https://speech.platform.bing.com/consumer/speech/synthesize/readaloud/voices/list?trustedclienttoken=' + trustedClientToken
def terminator(signo, stack_frame): sys.exit()
signal.signal(signal.SIGINT, terminator)
signal.signal(signal.SIGTERM, terminator)
def connectId(): return str(uuid.uuid4()).replace("-", "") def connectId(): return str(uuid.uuid4()).replace("-", "")
def removeIncompatibleControlChars(s): def removeIncompatibleControlChars(s):
output = [] output = []
@@ -51,11 +48,14 @@ def mkssmlmsg(text="", voice="en-US-AriaNeural", pitchString="+0Hz", rateString=
message+="<voice name='" + voice + "'>" + "<prosody pitch='" + pitchString + "' rate ='" + rateString + "' volume='" + volumeString + "'>" + text + '</prosody></voice></speak>' message+="<voice name='" + voice + "'>" + "<prosody pitch='" + pitchString + "' rate ='" + rateString + "' volume='" + volumeString + "'>" + text + '</prosody></voice></speak>'
return message return message
async def run_tts(msg, sentenceBoundaryEnabled="false", wordBoundaryEnabled="false", codec="audio-24khz-48kbitrate-mono-mp3"): def bool_to_lower_str(x): return 'true' if x else 'false'
async def run_tts(msg, sentenceBoundary=False, wordBoundary=False, codec="audio-24khz-48kbitrate-mono-mp3"):
sentenceBoundary = bool_to_lower_str(sentenceBoundary)
wordBoundary = bool_to_lower_str(wordBoundary)
logging.debug("Doing %s!" % msg) logging.debug("Doing %s!" % msg)
async with websockets.connect(wssUrl, ssl=ssl_context) as ws: async with websockets.connect(wssUrl, ssl=ssl_context) as ws:
message='X-Timestamp:'+formatdate()+'\r\nContent-Type:application/json; charset=utf-8\r\nPath:speech.config\r\n\r\n' message='X-Timestamp:'+formatdate()+'\r\nContent-Type:application/json; charset=utf-8\r\nPath:speech.config\r\n\r\n'
message+='{"context":{"synthesis":{"audio":{"metadataoptions":{"sentenceBoundaryEnabled":"'+sentenceBoundaryEnabled+'","wordBoundaryEnabled":"'+wordBoundaryEnabled+'"},"outputFormat":"' + codec + '"}}}}\r\n' message+='{"context":{"synthesis":{"audio":{"metadataoptions":{"sentenceBoundaryEnabled":"'+sentenceBoundary+'","wordBoundaryEnabled":"'+wordBoundary+'"},"outputFormat":"' + codec + '"}}}}\r\n'
await ws.send(message) await ws.send(message)
logging.debug("> %s" % message) logging.debug("> %s" % message)
await ws.send(msg) await ws.send(msg)
@@ -126,16 +126,14 @@ async def main():
logging.debug("reading from %s" % args.file) logging.debug("reading from %s" % args.file)
with open(args.file, 'r') as file: with open(args.file, 'r') as file:
args.text = file.read() args.text = file.read()
sentenceBoundaryEnabled = 'true' if args.enable_sentence_boundary else 'false'
wordBoundaryEnabled = 'true' if args.enable_word_boundary else 'false'
if args.custom_ssml: if args.custom_ssml:
async for i in run_tts(mkssmlmsg(text=args.text, customspeak=True), sentenceBoundaryEnabled, wordBoundaryEnabled, args.codec): async for i in run_tts(mkssmlmsg(text=args.text, customspeak=True), args.enable_sentence_boundary, args.enable_word_boundary, args.codec):
sys.stdout.buffer.write(i) sys.stdout.buffer.write(i)
else: else:
overhead = len(mkssmlmsg('', args.voice, args.pitch, args.rate, args.volume).encode('utf-8')) overhead = len(mkssmlmsg('', args.voice, args.pitch, args.rate, args.volume).encode('utf-8'))
wsmax = 65536 - overhead wsmax = 65536 - overhead
for text in _minimize(escape(removeIncompatibleControlChars(args.text)), b" ", wsmax): for text in _minimize(escape(removeIncompatibleControlChars(args.text)), b" ", wsmax):
async for i in run_tts(mkssmlmsg(text.decode('utf-8'), args.voice, args.pitch, args.rate, args.volume), sentenceBoundaryEnabled, wordBoundaryEnabled, args.codec): async for i in run_tts(mkssmlmsg(text.decode('utf-8'), args.voice, args.pitch, args.rate, args.volume), args.enable_sentence_boundary, args.enable_word_boundary, args.codec):
sys.stdout.buffer.write(i) sys.stdout.buffer.write(i)
elif args.list_voices: elif args.list_voices:
seperator = False seperator = False
@@ -150,4 +148,7 @@ async def main():
seperator = True seperator = True
if __name__ == "__main__": if __name__ == "__main__":
def terminator(signo, stack_frame): sys.exit()
signal.signal(signal.SIGINT, terminator)
signal.signal(signal.SIGTERM, terminator)
asyncio.get_event_loop().run_until_complete(main()) asyncio.get_event_loop().run_until_complete(main())