mirrors/edge-tts
1
0
Fork 0
mirror of https://github.com/rany2/edge-tts synced 2024-11-22 01:45:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

added pitch variable back.

Browse Source
This commit is contained in:
scott306lr 2023-08-31 05:19:57 +08:00
parent 8f8a334203
commit afd4ba8fee
2 changed files with 13 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -72,8 +72,6 @@ It is possible to make minor changes to the generated speech.
In addition, it is required to use `--rate=-50%` instead of `--rate -50%` (note the lack of an equal sign) otherwise the `-50%` would be interpreted as just another argument.
**NOTE**: `--pitch` was removed in 6.0.3 as it no longer appears to have any effect.
### Note on the `edge-playback` command
`edge-playback` is just a wrapper around `edge-tts` that plays back the generated speech. It takes the same arguments as the `edge-tts` option.

19
src/edge_tts/communicate.py
View File

@ -152,7 +152,7 @@ def split_text_by_byte_length(
yield new_text
def mkssml(text: Union[str, bytes], voice: str, rate: str, volume: str) -> str:
def mkssml(text: Union[str, bytes], voice: str, rate: str, volume: str, pitch: str) -> str:
"""
Creates a SSML string from the given parameters.
@ -164,7 +164,7 @@ def mkssml(text: Union[str, bytes], voice: str, rate: str, volume: str) -> str:
ssml = (
"<speak version='1.0' xmlns='http://www.w3.org/2001/10/synthesis' xml:lang='en-US'>"
f"<voice name='{voice}'><prosody pitch='+0Hz' rate='{rate}' volume='{volume}'>"
f"<voice name='{voice}'><prosody pitch='{pitch}' rate='{rate}' volume='{volume}'>"
f"{text}</prosody></voice></speak>"
)
return ssml
@ -203,7 +203,7 @@ def ssml_headers_plus_data(request_id: str, timestamp: str, ssml: str) -> str:
)
def calc_max_mesg_size(voice: str, rate: str, volume: str) -> int:
def calc_max_mesg_size(voice: str, rate: str, volume: str, pitch: str) -> int:
"""Calculates the maximum message size for the given voice, rate, and volume.
Returns:
@ -215,7 +215,7 @@ def calc_max_mesg_size(voice: str, rate: str, volume: str) -> int:
ssml_headers_plus_data(
connect_id(),
date_to_string(),
mkssml("", voice, rate, volume),
mkssml("", voice, rate, volume, pitch),
)
)
+ 50 # margin of error
@ -235,6 +235,7 @@ class Communicate:
*,
rate: str = "+0%",
volume: str = "+0%",
pitch: str = "+0Hz",
proxy: Optional[str] = None,
):
"""
@ -289,6 +290,12 @@ class Communicate:
raise ValueError(f"Invalid volume '{volume}'.")
self.volume: str = volume
if not isinstance(pitch, str):
raise TypeError("pitch must be str")
if re.match(r"^[+-]\d+Hz$", pitch) is None:
raise ValueError(f"Invalid pitch '{pitch}'.")
self.pitch: str = pitch
if proxy is not None and not isinstance(proxy, str):
raise TypeError("proxy must be str")
self.proxy: Optional[str] = proxy
@ -298,7 +305,7 @@ class Communicate:
texts = split_text_by_byte_length(
escape(remove_incompatible_characters(self.text)),
calc_max_mesg_size(self.voice, self.rate, self.volume),
calc_max_mesg_size(self.voice, self.rate, self.volume, self.pitch),
)
final_utterance: Dict[int, int] = {}
prev_idx = -1
@ -362,7 +369,7 @@ class Communicate:
ssml_headers_plus_data(
connect_id(),
date,
mkssml(text, self.voice, self.rate, self.volume),
mkssml(text, self.voice, self.rate, self.volume, self.pitch),
)
)