blackteay/GPT-SoVITS
1
0
Fork 0
mirror of https://github.com/RVC-Boss/GPT-SoVITS.git synced 2026-07-09 00:01:12 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge 61afcf2600646fca8e27b412cd9564fefb6a6678 into 1a9b8854ee510b43a2a737f4e1278fb31a68d224

Browse Source
This commit is contained in:
jackwu982 2025-06-13 01:49:53 +08:00 committed by GitHub
commit 9d77a88f0b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
api_v2.py
View File

@ -22,7 +22,7 @@ POST:
```json
{
"text": "", # str.(required) text to be synthesized
"text_lang: "", # str.(required) language of the text to be synthesized
"text_lang": "", # str.(required) language of the text to be synthesized
"ref_audio_path": "", # str.(required) reference audio path
"aux_ref_audio_paths": [], # list.(optional) auxiliary reference audio paths for multi-speaker tone fusion
"prompt_text": "", # str.(optional) prompt text for the reference audio
@ -33,7 +33,7 @@ POST:
"text_split_method": "cut0", # str. text split method, see text_segmentation_method.py for details.
"batch_size": 1, # int. batch size for inference
"batch_threshold": 0.75, # float. threshold for batch splitting.
"split_bucket: True, # bool. whether to split the batch into multiple buckets.
"split_bucket": True, # bool. whether to split the batch into multiple buckets.
"speed_factor":1.0, # float. control the speed of the synthesized audio.
"streaming_mode": False, # bool. whether to return a streaming response.
"seed": -1, # int. random seed for reproducibility.
@ -305,7 +305,7 @@ async def tts_handle(req: dict):
req (dict):
{
"text": "", # str.(required) text to be synthesized
"text_lang: "", # str.(required) language of the text to be synthesized
"text_lang": "", # str.(required) language of the text to be synthesized
"ref_audio_path": "", # str.(required) reference audio path
"aux_ref_audio_paths": [], # list.(optional) auxiliary reference audio paths for multi-speaker synthesis
"prompt_text": "", # str.(optional) prompt text for the reference audio
@ -316,7 +316,7 @@ async def tts_handle(req: dict):
"text_split_method": "cut5", # str. text split method, see text_segmentation_method.py for details.
"batch_size": 1, # int. batch size for inference
"batch_threshold": 0.75, # float. threshold for batch splitting.
"split_bucket: True, # bool. whether to split the batch into multiple buckets.
"split_bucket": True, # bool. whether to split the batch into multiple buckets.
"speed_factor":1.0, # float. control the speed of the synthesized audio.
"fragment_interval":0.3, # float. to control the interval of the audio fragment.
"seed": -1, # int. random seed for reproducibility.