firebase-js-sdk/.changeset/cool-bugs-pump.md at main

mirror of https://github.com/hanzoai/firebase-js-sdk.git synced 2026-09-24 16:59:10 +00:00

Files

T

sedanah-mandGitHub e88c1c4126 feat(ai): support text-to-speech capabilities (single & multi-speaker configurations) for non-Live API models (#10145 )

* feat(ai): implementmulti-speaker speech config; includes tests

* add changeset, fix typo

* fix: yarn format

* fix changeset

* fix changeset typo

* remove unnecessary tests; fix interface description to match proposal

* Generate documentation

* fix: yarn format & lint fix

* add more descriptive changeset

* Adds tests for speech config to check if its correctly passed through to the API requests for both generateContent and generateContentStream methods

* yarn format

* yarn format

* Refine changeset file description

* Fix typo

* format fix

* update description BaseSpeechConfig

* update descriptions

* format doc

* yarn format

* fix @ typo over MultiSpeakerSpeechConfig

* fix: adjusted description wording for the interfaces; fix: public tags to beta

* fix: formatting using @remarks

* fix: typo

* yarn format

* run yarn docgen:all

* update SpeechConfig to beta

* update speech config to beta

* upd SingleSpeakerSpeechConfig description

* doc generation

2026-07-27 13:40:50 -07:00

200 B

Raw Permalink Blame History

@firebase/ai, firebase

@firebase/ai	firebase
minor	minor

Added support for text-to-speech capabilities (both single- and multi-speaker configurations) for non-Live API models (for example, Gemini TTS models).

200 B Raw Permalink Blame History

200 B

Raw Permalink Blame History