161 commits

Author	SHA1	Message	Date
Fireblade2534	fd86395e98	Reverted the kokoro version bump and change the phenomizer to use the phenomizer that the rest of the text uses.	2025-03-31 13:28:44 +00:00
fondoger	88f19d7751	Improve text normalize to keep original timestamps	2025-03-30 21:31:17 +08:00
Fireblade2534	d712308f98	Fixes relating to parsing money and tests. Also readme stuff	2025-03-21 18:03:09 +00:00
Fireblade2534	c24aeefbb2	Aculy fixed tests this time	2025-03-20 19:15:07 +00:00
Fireblade2534	c902b2ca0d	probably fix tests	2025-03-20 16:27:18 +00:00
Fireblade2534	8f23bf53a4	Inital test commit of segfault fixes	2025-03-20 16:20:28 +00:00
remsky	0d7570ab50	Merge pull request #240 from fireblade2534/fixes	2025-03-18 04:27:17 -06:00
Fireblade	9f9e9b601e	Fixes not returning a download link if streaming is off and return_download_link is true	2025-03-13 16:23:49 -04:00
Fireblade2534	acb7d05515	Merge branch 'master' into master	2025-03-12 11:17:44 -04:00
remsky	e4744f5545	Merge pull request #235 from fireblade2534/fixes	2025-03-12 02:22:04 -06:00
Fireblade	aa403f2070	Adds the ability to subtract voices	2025-03-11 14:28:48 -04:00
Fireblade2534	dafc87ddef	Merge pull request #199 from blakkd/master ... converted CRLF ending lines to LF ones in api/src/structures/custom_responses.py	2025-03-10 18:14:29 -04:00
Cong Nguyen	9a9bc4aca9	added support for mps on mac with apple silicon	2025-03-10 11:58:45 +11:00
Fireblade2534	f2c5bc1b71	Merge branch 'remsky:master' into fixes	2025-03-02 21:39:17 -05:00
Fireblade	b3d5f4de08	fixes and corrections to code that didn't cause errors but didn't really make sense	2025-03-02 21:36:34 -05:00
Fireblade2534	d67570ab21	Merge pull request #210 from fireblade2534/preserve-custom-phenomes ... This fix allows for inputing custom pronuncations through text. For example: "This is a test of a [bla bla](/ðɪs ɪz ˈoʊnli ɐ tˈɛst/) system." It ensures that normalization does not affect custom prnouncations	2025-03-02 14:37:07 -05:00
Fireblade2534	43576c4a76	Remove random 1	2025-03-01 12:45:41 -05:00
Fireblade	226a75e782	fixes the low quality fix not working properly	2025-02-28 21:57:33 -05:00
Fireblade	f415ce7109	don't replace brackets as that is handled in misaki	2025-02-28 21:39:12 -05:00
Fireblade	906cf77a65	preserve custom phenomes	2025-02-28 21:37:46 -05:00
Fireblade	9247bc3a12	notremoved the rate argument which apperently means bitrate	2025-02-26 21:51:00 -05:00
Fireblade	980bc5b4a8	Fix low quality because audio was being encoded at a lower bitrate	2025-02-26 20:52:38 -05:00
blakkd	3c5029f801	converted CRLF ending lines to LF ones in api/src/structures/custom_responses.py ... let ruff organise the imports	2025-02-24 02:11:48 +01:00
Fireblade	5de3cace3b	Fix some tests and allow running the docker container offline	2025-02-22 15:17:28 -05:00
Fireblade	c1207f085b	Merge remote-tracking branch 'upstream/master' into streaming-word-timestamps	2025-02-22 14:58:28 -05:00
remsky	39cc056fe2	Merge pull request #179 from fireblade2534/normalization-changes	2025-02-21 20:00:15 -07:00
Fireblade	c5a3e13670	Converted the stream writer to use pyav	2025-02-19 23:10:51 -05:00
Fireblade	4ee4d36822	Fixes a couple of issues with audio triming and prevents errors with single voice weights	2025-02-18 18:12:49 -05:00
Fireblade	7f15ba8fed	Add a .gitattributes	2025-02-18 17:44:03 -05:00
Fireblade	f2b2f41412	fixed wrong varible name bug	2025-02-16 17:07:41 -05:00
Fireblade	cb22aab239	Fix streaming a wav file with captions not reaturning any captions (This is only a problem because wav streaming does not acually work)	2025-02-16 16:49:33 -05:00
Fireblade	e3dc959775	Simplify code so erverything uses AudioChunks	2025-02-16 15:37:01 -05:00
Fireblade	9c0e328318	made it skip text normalization when using other languages as it only supports english	2025-02-16 14:16:18 -05:00
Fireblade	41598eb3c5	better parsing for times and phone numbers	2025-02-15 19:02:57 -05:00
Fireblade	3290bada2e	changes to how money and numbers are handled	2025-02-15 17:48:12 -05:00
Fireblade	4802128943	Replaced default voice with af_heart as af doesn't exist	2025-02-15 12:36:36 -05:00
Fireblade	8c457c3292	fixed final test	2025-02-15 09:49:15 -05:00
Fireblade	1a6e7abac3	fixed a bunch of tests	2025-02-15 09:40:01 -05:00
Fireblade	1a03ac7464	Fixed some tests	2025-02-14 15:00:47 -05:00
Fireblade	353fe79690	fix small error	2025-02-14 14:39:24 -05:00
Fireblade	842d056552	Merge branch 'streaming-word-timestamps' of https://github.com/fireblade2534/Kokoro-FastAPI into streaming-word-timestamps	2025-02-14 14:36:20 -05:00
Fireblade	9c1ced237b	Cleaned up some code and fixed an error in the readme	2025-02-14 14:36:17 -05:00
Fireblade2534	b71bab45d4	Merge branch 'master' into streaming-word-timestamps	2025-02-14 14:32:41 -05:00
Fireblade	34acb17682	Mostly completed work on refractoring a bunch of code as well as streaming word level time stamps	2025-02-14 14:29:47 -05:00
Fireblade	0b5ec320c7	streaming word level time stamps	2025-02-14 13:37:42 -05:00
Fireblade	4027768920	Started work on allowing streaming word level timestamps as well as transitioning the dev code so it uses a lot more from the open ai endpoint	2025-02-13 18:00:03 -05:00
Fireblade	7772dbc2e4	fixed no stream file writing	2025-02-13 16:12:51 -05:00
remsky	cfae7db7fc	fix: bump up audio quality settings in StreamingAudioWriter	2025-02-13 00:22:14 -07:00
remsky	37ea01eaf9	fix: download_format option for audio response, handling in create_speech	2025-02-13 00:04:21 -07:00
remsky	f585185404	Update openai_compatible.py	2025-02-12 23:31:47 -07:00