# `Parlora.Providers.Gemini`
[🔗](https://github.com/hfiguera/parlora/blob/v0.1.0/lib/parlora/providers/gemini.ex#L1)

Gemini 3.8 Live with application-owned credentials and backend work.

Speakable context is sent as a function response or an application content turn.
A content turn triggers a response and may interrupt active model generation.
Submission is reported as unconfirmed, never as a remote acknowledgment.
Quiet context and live system-instruction changes are unsupported.

# `audio_limits`

Finite session limits for generated audio bursts; pass as session :limits, with optional overrides.

# `child_spec`

Returns a specification to start this module under a supervisor.

See `Supervisor`.

---

*Consult [api-reference.md](api-reference.md) for complete listing*