Google Gemini Provider Guide
A single Google Gemini account can power all six Insights services. Gemini is the only provider with a native path to every service, which makes it the simplest single-vendor deployment.
Two Gemini APIs are used, and the distinction matters when you configure options:
- Gemini Live (
BidiGenerateContent) — a bidirectional WebSocket used bytranscription(text responses) andai_agent(audio responses). - Gemini REST models —
Models.GenerateContentfor translation and chat, the Interactions API for speech synthesis, the Files API +Batches.Createfor meeting summarization.
Both Live and the Interactions API require api_version: "v1beta".
Supported Services
| Service | Gemini path | Default model |
|---|---|---|
transcription | Gemini Live BidiGenerateContent, ResponseModalities=[TEXT] | gemini-3.5-transcribe-live |
translation | Models.GenerateContent with ResponseMIMEType: application/json | gemini-3.1-flash-lite |
speech-synthesis | Gemini Interactions API returning audio/L16 PCM16 | gemini-3.8-flash-tts |
ai_text_chat | Streaming chat, up to 8 rounds of MCP tool calling | required, for example gemini-3.1-flash |
meeting_summarizing | Files API upload plus Batches.Create batch job | required, for example gemini-3.1-flash-lite |
ai_agent | Gemini Live BidiGenerateContent, ResponseModalities=[AUDIO] | gemini-3.8-live |
Get an API key from Google AI Studio or Google Cloud, then define one account and reference it from every service.
Provider Account Configuration
insights:
providers:
google:
- id: "default-gemini-creds"
credentials:
api_key: "YOUR_GEMINI_API_KEY"
options:
api_version: "v1beta"
| Key | Type | Required | Description |
|---|---|---|---|
id | string | Yes | Unique account name. Services reference it, for example "default-gemini-creds". |
credentials.api_key | string | Yes | Gemini API key. |
options.api_version | string | No | API version. Set "v1beta", which is required for Gemini Live (transcription, ai_agent) and for the Interactions API (speech-synthesis). |
options.endpoint | string | No | Custom gateway or proxy base URL. Leave empty to call Google directly. |
options.auth_header | string | No | Header used to carry the key when a gateway is in front of Gemini. "Authorization" sends Authorization: Bearer <api_key>. Any other name sends <header>: <api_key>. |
Service Configuration
transcription
Streams the microphone tracks of allowed speakers to Gemini Live and receives text deltas. Live is opened with ResponseModalities=[TEXT], so the model never returns audio for this service.
transcription:
provider: "google"
id: "default-gemini-creds"
options:
model: "gemini-3.5-transcribe-live"
transcribe_mode: "VERBATIM"
api_version: "v1beta"
max_selected_trans_langs: 2
pricing:
default:
price_per_hour: 0.36
| Key | Type | Default | Description |
|---|---|---|---|
options.model | string | "gemini-3.5-transcribe-live" | Live transcription model. |
options.transcribe_mode | string | "VERBATIM" | "VERBATIM" transcribes word for word. "SMART" lets the model normalize and clean up speech. |
options.api_version | string | "v1beta" | Required for BidiGenerateContent. |
options.max_selected_trans_langs | integer | 2 | Maximum simultaneous caption languages per room. Enforced server-side; a host cannot raise it from the API. |
translation
Translates a batch of strings into every configured target language in a single GenerateContent call. The request sets ResponseMIMEType: application/json, so the model returns one JSON object instead of prose, which keeps multi-language chat translation to one round trip.
translation:
provider: "google"
id: "default-gemini-creds"
options:
translate_model: "gemini-3.1-flash-lite"
max_selected_trans_langs: 5
pricing:
default:
price_per_million_characters: 10.00
| Key | Type | Default | Description |
|---|---|---|---|
options.translate_model | string | "gemini-3.1-flash-lite" | Translation model. model is accepted as an alias. |
options.max_selected_trans_langs | integer | 5 | Maximum target languages for chat and caption translation. Separate from the transcription limit. |
speech-synthesis
Calls the Gemini Interactions API and reads PCM16 audio (audio/L16) straight from the response, so no file is written to disk.
speech-synthesis:
provider: "google"
id: "default-gemini-creds"
options:
model: "gemini-3.8-flash-tts"
default_voice: "Kore"
tts_sample_rate: 16000
api_version: "v1beta"
pricing:
default:
price_per_million_characters: 16.00
| Key | Type | Default | Description |
|---|---|---|---|
options.model | string | "gemini-3.8-flash-tts" | TTS model. |
options.default_voice | string | "Kore" | Voice used when a language has no explicit voice mapping. |
options.tts_sample_rate | integer | 16000 | PCM sample rate. Allowed values: 8000, 16000, 24000. |
options.api_version | string | "v1beta" | Required by the Interactions API. |
Gemini uses one default_voice for every language rather than a per-language voice map. If you need distinct voices per target language, use the Microsoft Azure guide.
ai_text_chat
Streaming chat for moderators (room copilot) and participants (learning assistant). The moderator path can call MCP room tools for up to 8 rounds before it must answer.
ai_text_chat:
provider: "google"
id: "default-gemini-creds"
options:
chat_model: "gemini-3.1-flash-Preview"
summarize_model: "gemini-3.1-flash-lite"
context_window: 5
pricing:
"gemini-3.1-flash-Preview":
input_price_per_million_tokens: 0.30
output_price_per_million_tokens: 2.50
"gemini-3.1-flash-lite":
input_price_per_million_tokens: 0.10
output_price_per_million_tokens: 0.40
| Key | Type | Required | Description |
|---|---|---|---|
options.chat_model | string | Yes | Model for the live conversation and tool calling. |
options.summarize_model | string | No | Model used to condense long context. |
options.context_window | integer | No, default 5 | Number of recent messages kept verbatim per conversation. |
meeting_summarizing
Uploads the mixed room recording through the Gemini Files API, then runs a batch job with Batches.Create and stores the returned summary text. Uploads are removed after the job finishes.
meeting_summarizing:
provider: "google"
id: "default-gemini-creds"
options:
summarize_model: "gemini-3.1-flash-lite"
pricing:
default:
input_price_per_million_tokens: 0.30
output_price_per_million_tokens: 2.50
| Key | Type | Required | Description |
|---|---|---|---|
options.summarize_model | string | Yes | Model used for the batch summarization job. |
Custom prompts for the summary are set per room, not here. See AI Meeting Summarization.
ai_agent
Runs the voice and vision agent on Gemini Live with ResponseModalities=[AUDIO]: the model hears the room audio, sees whiteboard and share frames, calls agent tools, and speaks back.
ai_agent:
provider: "google"
id: "default-gemini-creds"
options:
realtime_model: "gemini-3.8-live"
summarize_model: "gemini-3.1-flash-lite"
api_version: "v1beta"
pricing:
realtime_model:
input_price_per_million_tokens: 0.75
cached_input_price_per_million_tokens: 0.075
cache_write_input_price_per_million_tokens: 0.9375
audio_input_price_per_million_tokens: 3.00
audio_cached_input_price_per_million_tokens: 0.30
audio_cache_write_input_price_per_million_tokens: 3.75
image_input_price_per_million_tokens: 1.00
image_cached_input_price_per_million_tokens: 0.10
image_cache_write_input_price_per_million_tokens: 1.25
output_price_per_million_tokens: 4.50
audio_output_price_per_million_tokens: 12.00
summarize_model:
input_price_per_million_tokens: 0.25
output_price_per_million_tokens: 1.50
| Key | Type | Default | Description |
|---|---|---|---|
options.realtime_model | string | "gemini-3.8-live" | Live model used for the session. |
options.summarize_model | string | none | Model used for the end-of-session summary. If omitted, the server reuses the summary model from ai_text_chat or meeting_summarizing, and otherwise writes a deterministic local summary with no LLM call. |
options.api_version | string | "v1beta" | Required for BidiGenerateContent. |
The agent voice is selected per room with ai_agent_features.voice, not in server configuration. Server-side options only choose models and the API version.
Pricing Configuration
Prices only drive the estimated_cost field on usage artifacts; they never change what Google bills you. Rates are per million tokens for LLM services and per hour or per million characters for speech.
transcription
pricing.default.price_per_hour prices SPEECH_TRANSCRIPTION_USAGE from transcribed duration.
translation
pricing.default.price_per_million_characters prices translation output.
CHAT_TRANSLATION_USAGE is metered by character count, not tokens, and is priced with pricing.default.price_per_million_characters. Set an explicit rate or translation cost estimates stay at zero.
speech-synthesis
pricing.default.price_per_million_characters prices SYNTHESIZED_SPEECH_USAGE from the number of characters sent to TTS.
ai_text_chat
pricing.<chat_model> and pricing.<summarize_model> use input_price_per_million_tokens and output_price_per_million_tokens. Quote model names that contain dots or uppercase characters. A pricing.default entry applies to any model without its own block.
meeting_summarizing
pricing.<summarize_model> (or pricing.default) uses input_price_per_million_tokens and output_price_per_million_tokens.
ai_agent
Token pricing is multimodal. Put rates under pricing.realtime_model (or under the concrete model name) and under pricing.summarize_model:
| Key | Covers |
|---|---|
input_price_per_million_tokens | Text input |
cached_input_price_per_million_tokens | Cached text input |
cache_write_input_price_per_million_tokens | Text written to the prompt cache |
audio_input_price_per_million_tokens | Participant speech sent to the model |
audio_cached_input_price_per_million_tokens | Cached audio input |
audio_cache_write_input_price_per_million_tokens | Audio written to the prompt cache |
image_input_price_per_million_tokens | Whiteboard and share frames |
image_cached_input_price_per_million_tokens | Cached image input |
image_cache_write_input_price_per_million_tokens | Images written to the prompt cache |
output_price_per_million_tokens | Text output, including thinking tokens |
audio_output_price_per_million_tokens | Synthesized agent speech |
Cache rates are optional. Missing cache rates are estimated at the uncached input rate. The usage fields these rates fill are listed in Summaries & Usage Artifacts.
Complete Configuration Example
Every service on Gemini, one account:
insights:
enabled: true
providers:
google:
- id: "default-gemini-creds"
credentials:
api_key: "YOUR_GEMINI_API_KEY"
options:
api_version: "v1beta"
services:
transcription:
provider: "google"
id: "default-gemini-creds"
options:
model: "gemini-3.5-transcribe-live"
transcribe_mode: "VERBATIM"
api_version: "v1beta"
max_selected_trans_langs: 2
pricing:
default:
price_per_hour: 0.36
translation:
provider: "google"
id: "default-gemini-creds"
options:
translate_model: "gemini-3.1-flash-lite"
max_selected_trans_langs: 5
pricing:
default:
price_per_million_characters: 10.00
speech-synthesis:
provider: "google"
id: "default-gemini-creds"
options:
model: "gemini-3.8-flash-tts"
default_voice: "Kore"
tts_sample_rate: 16000
api_version: "v1beta"
pricing:
default:
price_per_million_characters: 16.00
ai_text_chat:
provider: "google"
id: "default-gemini-creds"
options:
chat_model: "gemini-3.1-flash-Preview"
summarize_model: "gemini-3.1-flash-lite"
context_window: 5
pricing:
default:
input_price_per_million_tokens: 0.30
output_price_per_million_tokens: 2.50
meeting_summarizing:
provider: "google"
id: "default-gemini-creds"
options:
summarize_model: "gemini-3.1-flash-lite"
pricing:
default:
input_price_per_million_tokens: 0.30
output_price_per_million_tokens: 2.50
ai_agent:
provider: "google"
id: "default-gemini-creds"
options:
realtime_model: "gemini-3.8-live"
summarize_model: "gemini-3.1-flash-lite"
api_version: "v1beta"
pricing:
realtime_model:
input_price_per_million_tokens: 0.75
cached_input_price_per_million_tokens: 0.075
cache_write_input_price_per_million_tokens: 0.9375
audio_input_price_per_million_tokens: 3.00
audio_cached_input_price_per_million_tokens: 0.30
audio_cache_write_input_price_per_million_tokens: 3.75
image_input_price_per_million_tokens: 1.00
image_cached_input_price_per_million_tokens: 0.10
image_cache_write_input_price_per_million_tokens: 1.25
output_price_per_million_tokens: 4.50
audio_output_price_per_million_tokens: 12.00
summarize_model:
input_price_per_million_tokens: 0.25
output_price_per_million_tokens: 1.50
Common Pitfalls
- Missing
api_version: "v1beta". Gemini Live (transcription,ai_agent) and the Interactions API (speech-synthesis) fail on other versions. Set it on the account, on each of those services, or both. - Unquoted model names. Quote model names such as
"gemini-3.1-flash-Preview", and always quote pricing keys that contain dots or uppercase characters. - Empty pricing block. Without rates the session still runs, but usage artifacts report zero cost.
Related Pages
- Server & Provider Setup: shared provider structure, capability matrix, and BYOK.
- Live Captions, STT & Translation: how the hidden
RoomAgentstreams audio. - AI Meeting Summarization: capture, prompts, and batch job behavior.
- AI Text Chat & Room Copilot: moderator tool calling and memory.
- OpenAI & Self-Hosted Provider Guide
- Microsoft Azure Provider Guide