mushuiyu886
5ccfc97b31
fix(google): bound TTS success JSON response reads ( #96984 )
2026-06-27 07:00:36 -07:00
Vincent Koc
90cf265f29
refactor(google): share TTS request preparation
2026-06-22 19:38:30 +08:00
Peter Steinberger
96e5812426
docs: document medium extension sources
2026-06-04 21:33:54 -04:00
Vincent Koc
27b15a19e8
refactor(voice): catalog voice models through providers ( #87794 )
...
* refactor(providers): catalog voice models
* feat(tts): route speech through voice models
* refactor(tts): rename speaker selection fields
* refactor(tts): mark default speech models
* test(tts): type migrated speaker config assertions
* refactor(providers): avoid catalog merge map spread
* fix(tts): honor voice model fallbacks
* refactor(tts): move speech core into package
* chore(tts): register speech core knip workspace
* fix(tts): show migrated speaker voice in status
* fix(tts): satisfy speech core lint
* fix(tts): preserve explicit model aliases
* test(tts): narrow provider config assertion
* test(doctor): allow slow commitments repair check
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com >
2026-05-29 04:46:45 +01:00
Peter Steinberger
4f4d108639
chore(lint): remove underscore-dangle allow list ( #83542 )
...
* chore(lint): reduce underscore-dangle exceptions
* chore(lint): reduce more underscore exceptions
* chore(lint): remove underscore-dangle allow list
* fix(lint): repair underscore cleanup regressions
* test(lint): track version define suppression
2026-05-18 14:56:06 +01:00
Peter Steinberger
827b0de0ce
refactor: reduce plugin sdk surface
2026-05-10 12:37:10 +01:00
Vincent Koc
361737d1f1
fix(tts): honor telephony voice overrides
2026-05-03 22:52:18 -07:00
Peter Steinberger
a972c9ec45
test: tolerate transient google tts and openrouter tool probes
2026-04-29 14:46:28 +01:00
Barron Roth
0594fa3c4d
TTS: add provider personas
2026-04-26 09:42:38 +05:30
Peter Steinberger
e2fd3dcee9
fix(google): emit opus voice-note tts
2026-04-25 21:33:33 +01:00
Rohan Shiralkar
cab66c5556
fix(google): honor models.providers.google.request.allowPrivateNetwork in TTS
...
Image generation and media understanding both thread the
sanitized models.providers.google.request config (including
allowPrivateNetwork) into resolveGoogleGenerativeAiHttpRequestConfig.
Speech synthesis omitted that arg, so TTS always saw
allowPrivateNetwork: false regardless of config — silently falling
back to a different speech provider when the configured Google TTS
endpoint resolved to a private/internal IP (proxies, custom backends,
test mocks).
Mirror the image-generation-provider pattern: thread request through
synthesizeGoogleTtsPcm at both call sites (synthesize and
synthesizeTelephony).
Follow-up to #67216 .
2026-04-25 21:02:06 +01:00
Peter Steinberger
8acc92c881
feat(google): support Gemini TTS style profile
2026-04-25 06:11:23 +01:00
Peter Steinberger
a43c1f8807
refactor: share provider HTTP errors with google
2026-04-24 19:33:44 +01:00
Barron Roth
bf59917cd1
fix: add Google Gemini TTS provider ( #67515 ) (thanks @barronlroth)
...
* Add Google Gemini TTS provider
* Remove committed planning artifact
* Explain Google media provider type shape
* google: distill Gemini TTS provider
* fix: add Google Gemini TTS provider (#67515 ) (thanks @barronlroth)
* fix: honor cfg-backed Google TTS selection (#67515 ) (thanks @barronlroth)
* fix: narrow Google TTS directive aliases (#67515 ) (thanks @barronlroth)
---------
Co-authored-by: Ayaan Zaidi <hi@obviy.us >
2026-04-16 11:54:35 +05:30
