# Gemini Live API > Google's Live API runs real-time spoken conversations with Gemini audio-to-audio models over a stateful WebSocket. It takes audio, images and text, speaks back, and supports interruptions, function calling and Google Search grounding. - Canonical: https://www.anchorterminal.com/tools/gemini-live - Markdown: https://www.anchorterminal.com/tools/gemini-live.md (~9,100 tokens) - Slim: https://www.anchorterminal.com/tools/gemini-live.min.md (~2,030 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/tools/gemini-live.json (this page as data, same URL with Accept: application/json) - Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt) - API: https://www.anchorterminal.com/api/v1/index.json - Updated: 2026-10-09 ## Overview **Grade C · 57.1/100 · rank #560 of 842 · #7 in Conversational voice agents · not agent-ready · confidence medium** More from Google, listed separately because each is its own product: [Gemini Developer API](https://www.anchorterminal.com/tools/gemini-api.md) (Model APIs & inference), [Gemini Embedding](https://www.anchorterminal.com/tools/gemini-embedding.md) (Embeddings & rerankers), [Vertex AI Gemini tuning](https://www.anchorterminal.com/tools/vertex-ai-tuning.md) (Fine-tuning), [Google Cloud Model Armor](https://www.anchorterminal.com/tools/google-model-armor.md) (Guardrails & safety filters), [Google Imagen](https://www.anchorterminal.com/tools/google-imagen.md) (Image generation), [Google Veo](https://www.anchorterminal.com/tools/google-veo.md) (Video generation), [Google Lyria](https://www.anchorterminal.com/tools/google-lyria.md) (Music generation), [Google Cloud Speech-to-Text](https://www.anchorterminal.com/tools/google-speech-to-text.md) (Speech-to-text), [Agent Development Kit (ADK)](https://www.anchorterminal.com/tools/google-adk.md) (Agent frameworks & SDKs), [Google Cloud Secret Manager](https://www.anchorterminal.com/tools/google-secret-manager.md) (Secrets & credential vaults), [Google Weather API (Maps Platform)](https://www.anchorterminal.com/tools/google-weather-api.md) (Weather & climate data), [Chrome DevTools MCP](https://www.anchorterminal.com/tools/chrome-devtools-mcp.md) (Browser automation), [Google Maps Platform + Grounding Lite MCP](https://www.anchorterminal.com/tools/google-maps-platform.md) (Maps, geocoding & places), [Google Cloud Translation](https://www.anchorterminal.com/tools/google-cloud-translation.md) (Translation), [Google Calendar API](https://www.anchorterminal.com/tools/google-calendar-api.md) (Calendars & scheduling), [Firebase Cloud Messaging](https://www.anchorterminal.com/tools/firebase-cloud-messaging.md) (Notifications), [Google Drive API + MCP](https://www.anchorterminal.com/tools/google-drive-api.md) (File storage & sharing), [Gemini CLI](https://www.anchorterminal.com/tools/gemini-cli.md) (Agent harnesses), [Google Search Console API](https://www.anchorterminal.com/tools/google-search-console.md) (SEO & search visibility), [Google Ads API](https://www.anchorterminal.com/tools/google-ads-api.md) (Advertising & campaign operations), [Google Forms API](https://www.anchorterminal.com/tools/google-forms.md) (Forms, surveys & structured intake), [Google Sheets API](https://www.anchorterminal.com/tools/google-sheets-api.md) (Spreadsheets & operational tables), [Gmail API](https://www.anchorterminal.com/tools/gmail-api.md) (Mailbox access). ## Assessment A speech-to-speech API with per-token prices published, a free tier and a generally available model, `gemini-3.8-live`, since 15 September 2026. The documented raw WebSocket connection carries the API key in the URL, connections reset about every 10 minutes, and no SLA or readable incident history was found for the Developer API. ## Facts | Field | Value | | --- | --- | | Vendor | Google (https://ai.google.dev) | | Kind | HTTP API | | Category | Conversational voice agents (https://www.anchorterminal.com/categories/voice-agents) | | Transport | HTTP | | Endpoint | `https://generativelanguage.googleapis.com/v1beta` | | Auth | API key · Self-serve API key from Google AI Studio, tied to a Google Cloud project. Keys created since 28 May 2026 are authorisation keys bound to a service account and restricted to the Gemini API, and unrestricted standard keys are rejected. The raw WebSocket guide passes the key as a `key` query parameter. For browsers and phones, a backend mints an ephemeral token (preview) at `POST /v1beta/auth_tokens`, single use by default, 1 minute to start a session and 30 minutes to use it, optionally locked to a model and configuration. | | Pricing | Freemium ($14 / 1k req) · Free tier on the Live models with no billing account, where content is used to improve Google products. Paid tier per 1M tokens on `gemini-3.8-live`, the extended thinking model and `gemini-3.1-flash-live-preview`. Text in $0.75, audio in $3.00 (about $0.005 a minute), image or video in $1.00, text out $4.50, audio out $12.00 (about $0.018 a minute). Google Search grounding $14 per 1,000 queries after 5,000 free a month. Each turn re-bills the whole session context. Paid tier needs a linked billing account and a $5 minimum prepayment (https://ai.google.dev/gemini-api/docs/pricing, checked 2026-10-08). | | x402 | No · No x402, MPP or L402 in the Live API docs, the pricing page or the billing guide (checked 2026-10-08). | | Licence | Proprietary service under the Gemini API Additional Terms of Service. The Python and JavaScript SDKs are Apache-2.0 | | Packages | pypi: `google-genai`; npm: `@google/genai` | | Source | https://github.com/google-gemini/gemini-live-api-examples | | Docs | https://ai.google.dev/gemini-api/docs/live-api | | llms.txt | https://ai.google.dev/gemini-api/docs/llms.txt | | Last release | 2026-09-15 | | npm downloads / week | 29,486,957 | | PyPI downloads / week | 34,128,301 | | Architecture | Speech-to-speech. Native audio models take audio in and speak audio out over one stateful WebSocket, with optional text transcripts of both sides | | Endpoint | `wss://generativelanguage.googleapis.com/ws/google.ai.generativelanguage.v1beta.GenerativeService.BidiGenerateContent`, and `BidiGenerateContentConstrained` for ephemeral tokens | | Models | `gemini-3.8-live` (stable, default), `gemini-3.8-live-extended-thinking`, `gemini-3.1-flash-live-preview` and `gemini-2.5-flash-native-audio-preview-12-2025` (both with an earliest shutdown of 17 November 2026). `gemini-3.5-live-translate-preview` and `gemini-3.5-transcribe-live` use the same API | | Audio | Input raw 16-bit PCM at 16 kHz, images as JPEG at up to 1 frame a second, and text. Output raw 16-bit PCM at 24 kHz. Audio is the only response modality on native audio models | | Languages | The overview page says 70 and the capabilities guide lists 99. The model detects the spoken language without a language code | | Latency | No figure published in the docs read. Google describes the API as low latency | | Interruptions | Automatic voice activity detection by default, with start and end sensitivity, prefix padding and silence duration settings. Hybrid and manual modes. The server sends `interrupted: true` when the user barges in | | Tool calling | Function declarations and Google Search grounding. Non-blocking calls by default on `gemini-3.8-live`, with `SILENT`, `WHEN_IDLE` and `INTERRUPT` scheduling. No code execution, URL context or Google Maps. The client must send tool responses itself | | Telephony | None built in. Partner integrations such as Voximplant, LiveKit, Pipecat and Agora connect calls | | Session limits | Audio sessions 15 minutes and audio with video 2 minutes without context compression. A connection lasts about 10 minutes. Resumption handles are valid 2 hours. Context window 128k tokens on native audio models | | Credentials | API key from AI Studio, an authorisation key bound to a service account by default since 28 May 2026. Ephemeral tokens (preview) from `POST /v1beta/auth_tokens` with `uses`, `expireTime`, `newSessionExpireTime` and `liveConnectConstraints` | | Free tier | Live models are free of charge on the free tier, where content is used to improve Google products. Limits are shown in AI Studio | | Rate limits | Per project and usage tier, shown in AI Studio. Public figures are the spend limits of $10, $50 and $200 per 10 minutes on Tiers 1 to 3. No concurrent session figure in the public docs | | Data retention | 55 days for abuse monitoring. Up to 24 hours of session state when resumption is on. 30 days for Google Search grounding. Paid-tier content isn't used to improve Google products | | SDKs | `google-genai` v2.29.0 for Python and `@google/genai` v2.28.0 for JavaScript, both tagged 7 October 2026, Apache-2.0 | | Capabilities | voice.agent, voice.speech-to-speech, voice.tools | | Tags | hosted, freemium, free-tier, closed-source, speech-to-speech, websocket, streaming, python, typescript, llms-txt, api-key, function-calling | | JSON | https://www.anchorterminal.com/api/v1/tools/gemini-live.json | ## Score breakdown (methodology v0.4, October 2026 research run) Assessed 2026-10-08 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. "This run" is each category's share of the 100 points. | Category | Weight | This run | Score (0–100) | Points | | --- | --- | --- | --- | --- | | Reliability | 16% | 20 | 41 | 8.2 | | Performance | 10% | pending | pending | n/a | | Schema & documentation | 13% | 16.2 | 66 | 10.7 | | Agent ergonomics | 13% | 16.2 | 69 | 11.2 | | Security & auth | 14% | 17.5 | 48 | 8.4 | | Payments & pricing | 10% | 12.5 | 40 | 5.0 | | Task success | 10% | pending | pending | n/a | | Maintenance & community | 7% | 8.8 | 83 | 7.3 | | Transparency & trust (editorial 55, provenance 89) | 7% | 8.8 | 72 | 6.3 | | Negative events | up to −15 | up to −15 | none recorded | 0 | | **Total** | | | | **57.1 → C** | ### Why each score - Reliability 41: Graded as a hosted API on the Gemini Developer API. A status page exists at aistudio.google.com/status, but it is drawn by script and we could read no components or history on 8 October (10 of 20, and 5 of 30 for the incident line with no readable record). Session limits are published, 15 minutes for audio and 2 for audio with video without compression, connections of about 10 minutes, and spend limits of $10, $50 and $200 per 10 minutes on Tiers 1 to 3. Per-model request limits and concurrent sessions are shown only in AI Studio (8 of 15). The server sends a GoAway message with `timeLeft` before closing, session resumption handles last 2 hours, and the troubleshooting guide gives exponential backoff with jitter for 429 and 503 (12 of 15). No SLA found for the Developer API (0). `gemini-3.8-live` is stable and generally available since 15 September, but the endpoint is `v1beta`, ephemeral tokens are in preview and three docs pages still label the Live API a preview (6 of 10). - Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes. - Schema & documentation 66: No AsyncAPI or similar file for the WebSocket messages was found. The keyless Discovery document (revision 20261006) types `auth_tokens.create` and five related schemas, `BidiGenerateContentSetup` among them, but not the client and server messages (8 of 25). llms.txt with a Markdown twin of every page (10). The capabilities guide, model comparison table and best practices page say when to use each model, voice activity mode and tool behaviour (16 of 20). The reference at ai.google.dev/api/live lists every message with field types, enums such as `ActivityHandling`, `TurnCoverage` and the sensitivity levels, and required marks, as tables and not as a schema (12 of 15). Python and JavaScript examples on every guide, but no list of WebSocket close codes or Live error responses was found (8 of 15). Dated changelog and versioned model names, less 3 because the tools page omits the 3.8 models, the overview says 70 languages where the capabilities guide lists 99, and preview banners remain after general availability (12 of 15). - Agent ergonomics 69: Scored as an API. Context can be sized with sliding-window compression and a trigger token count, media resolution is configurable and `UsageMetadata` reports token counts (18 of 25). No lists to page. Output controls are turn coverage, optional transcription of either side and the compression window (12 of 20). Server signals an agent can act on are `interrupted`, `generationComplete`, GoAway and tool call cancellation, but there is no documented error catalogue for the socket (10 of 20). Session resumption makes reconnects safe, resuming does not spend a token use, and non-blocking function calls take `SILENT`, `WHEN_IDLE` or `INTERRUPT` scheduling. No idempotency guidance for tool side effects after an interruption (14 of 20). A session needs only a model and a response modality, voice activity detection is automatic, and there are official Python and JavaScript SDKs (15). - Security & auth 48: Keys created since 28 May 2026 are authorisation keys bound to a service account and restricted to the Gemini API, with IP and origin restrictions, a leak checklist and rejection of unrestricted standard keys. Ephemeral tokens add expiry and use counts (25 of 30). The WebSocket guide's documented method is the API key in a `key` query parameter, and ephemeral tokens in `access_token`, so we deduct 10 (15 of 30). Ephemeral tokens can be locked to a model and configuration and to one session, which keeps system instructions server side. There is no approval step for tool calls, which the client runs itself (12 of 20). The model hears callers and can ground on Google Search, and the best practices page covers guardrails in system instructions but not prompt injection (5 of 15). Opt-in logs exist for billed projects, and we did not confirm they cover Live sessions. Usage is visible per project (8 of 15). security.txt on google.com valid to 2030 with a vulnerability reward programme. No certification naming the Developer API was found (8 of 20). - Payments & pricing 40: No x402, MPP or L402 (0 of 40). Per-token prices with per-minute equivalents are published without a login (20). The Live models are free of charge on the free tier, and the billing guide says new accounts start there with billing linked only to move to the paid tier (20). A key needs a Google account and AI Studio, so a person signs up in a browser (0). - Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored. - Maintenance & community 83: `gemini-3.8-live` went generally available on 15 September 2026, 23 days before the check (30). Three dated Live entries in the last 90 days, the robotics streaming model on 30 July, `gemini-3.5-transcribe-live` on 26 August and the 3.8 Live models on 15 September (20). Closed service with a changelog updated several times a month. Support channels were not tested (10 of 15). Current official SDKs, `google-genai` v2.29.0 and `@google/genai` v2.28.0, both tagged 7 October with about weekly tags since August (15). Apache-2.0 SDKs with type-check workflows in the Python repository and Node 20 or later stated. CI results were not read (8 of 10). - Transparency & trust 72: Closed service with clear terms, SDKs under Apache-2.0 (15 of 30). The terms, pricing page and zero data retention page agree that free-tier content improves Google products and paid content does not. The terms say abuse logs are kept for a limited period and the abuse monitoring page gives 55 days. Session state is kept up to 24 hours when resumption is on, and Search grounding data 30 days (20 of 30). A deprecations table gives earliest shutdown dates and replacements, with 17 November 2026 for the two older Live previews, about nine weeks after the replacement shipped, and no stated minimum notice (15 of 20). The terms say data may be stored transiently or cached in any country where Google has facilities. The Data Processing Addendum applies to paid services, and no sub-processor list was read (5 of 20). Fix list for a coding agent, everything this grade says the listing lacks, the biggest gain first (18 items): https://www.anchorterminal.com/fixes/gemini-live.md (JSON https://www.anchorterminal.com/fixes/gemini-live.json) ### What we couldn't check - unchecked: the incident history and components on aistudio.google.com/status, which is drawn by script - unchecked: per-model request limits and concurrent session limits for the Live models, shown only at aistudio.google.com/rate-limit, a path robots.txt disallows - unchecked: whether opt-in AI Studio logs record Live API sessions - unchecked: GitHub star counts, because the GitHub API was rate limited - unchecked: the Live API on Vertex AI (Gemini Enterprise Agent Platform), its SLA, certifications and zero data retention terms. This listing grades the Gemini Developer API - unchecked: Google's sub-processor list and the Data Processing Addendum text - Whether Live responses are produced in 70 or 99 languages. The overview and the capabilities guide disagree - Whether the 24-hour session state retention on the zero data retention page and the 2-hour handle validity on the session page describe the same store - Go and Java SDK support for Live was not checked ### Sources - Live API overview (Markdown twin): (seen 2026-10-08) - capabilities guide, model comparison, limits and languages: (seen 2026-10-08) - session management: (seen 2026-10-08) - ephemeral tokens: (seen 2026-10-08) - WebSocket quickstart and authentication: (seen 2026-10-08) - tool use: (seen 2026-10-08) - best practices and billing model: (seen 2026-10-08) - Live API reference: (seen 2026-10-08) - gemini-3.8-live model page: (seen 2026-10-08) - pricing: (seen 2026-10-08) - rate limits: (seen 2026-10-08) - billing: (seen 2026-10-08) - release notes: (seen 2026-10-08) - deprecations: (seen 2026-10-08) - API keys: (seen 2026-10-08) - zero data retention: (seen 2026-10-08) - abuse monitoring: (seen 2026-10-08) - logs policy: (seen 2026-10-08) - troubleshooting and retry guidance: (seen 2026-10-08) - coding agent resources: (seen 2026-10-08) - Gemini API Additional Terms of Service: (seen 2026-10-08) - Google Privacy Policy: (seen 2026-10-08) - Discovery document: (seen 2026-10-08) - status page (not readable): (seen 2026-10-08) - security.txt: (seen 2026-10-08) - Python SDK tags: (seen 2026-10-08) - JavaScript SDK tags: (seen 2026-10-08) - npm latest version: (seen 2026-10-08) - example apps repository: (seen 2026-10-08) ## Who's behind it (provenance 89/100, checked 2026-10-08) | Check | Finding | Points | | --- | --- | --- | | Legal entity named | Google LLC | 20/20 | | Domain age | google.com, registered 1997-09-15 (29 years) | 15/15 | | Endpoint on the vendor's domain | generativelanguage.googleapis.com | 15/15 | | Terms of service | read, states 4 of the 7 things a reader expects, and has 3 clauses that cost points | 1.4/10 | | Privacy policy | read, states 7 of the 8 things a reader expects, and has 1 clause that costs points | 7.3/10 | | Status page | aistudio.google.com/status | 10/10 | | Changelog | published | 10/10 | | security.txt | valid | 10/10 | The WebSocket and the token endpoint are on generativelanguage.googleapis.com, Google's API domain. The docs are on ai.google.dev. RDAP for google.com gives a registration date of 1997-09-15. The Gemini API Additional Terms of Service are effective 23 March 2026 and incorporate the Google APIs Terms of Service. Paid services fall under Google's Data Processing Addendum for products where Google is a data processor. The Google Privacy Policy read on 8 October 2026 is effective 1 October 2026. It is Google's general policy, and the terms page is where API data use is set out. www.google.com/.well-known/security.txt expires 2030-04-01 and points to g.co/vulnz and the vulnerability reward programme. ai.google.dev has no security.txt of its own (404). aistudio.google.com/status answered 200 with a page drawn by script, so no component or incident history was read. ### Terms and privacy, as read A reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice. **Terms of service** (https://ai.google.dev/gemini-api/terms), read 2026-10-08, dated 2026-04-28, states 4 of the 7 things a reader expects. - To know. Says it may use customer content to train or improve models, and no opt-out was found (costs points). "When you use Unpaid Services, including, for example, Google AI Studio and the unpaid quota on Gemini API, Google uses the content you submit to the Services and any generated responses to provide, improve, and develop Google products and services and machine learning technologies, including Google's enterprise featur…" - To know. Restricts automated access (costs points). "scrape or export any Google Maps Data;" - To know. Restricts benchmarking or competitive use (costs points). "You may not use the Services to develop models that compete with the Services (e.g., Gemini API or Google AI Studio)." - Gives the date it was last updated. Last updated 2026-04-28. - Not found in the text. States a limit on its liability. - Not found in the text. Says how changes to the terms are announced. - Not found in the text. Refers to a service level or uptime commitment. - Also in the text (2026-10-08). The agentic services section, which names the Computer Use API, says the customer will not automatically bypass any requests for human confirmation. "You will not automatically bypass any requests for human confirmation." - Also in the text (2026-10-08). On the unpaid services, human reviewers may read, annotate and process API input and output. "To help with quality and improve our products, human reviewers may read, annotate, and process your API input and output." - Also in the text (2026-10-08). Customers may not cache, analyse, train on or otherwise learn from Grounded Results or Search Suggestions returned by Grounding with Google Search. "You will not, and will not allow your end user or any third party to, cache, frame, syndicate, resell, analyze, train on, or otherwise learn from Grounded Results or Search Suggestions." **Privacy policy** (https://policies.google.com/privacy), read 2026-10-08, dated 2026-10-01, states 7 of the 8 things a reader expects. - To know. Says it may use customer content to train or improve models, and no opt-out was found (costs points). "We use your interactions with AI models and technologies like Gemini Apps to develop, train, fine-tune, and improve these models to better handle your requests, and update their classifiers and filters including for safety, language understanding, and factuality." - Gives the date it was last updated. Last updated 2026-10-01. - Not found in the text. Says where data is transferred or stored. - Also in the text (2026-10-08). Members of organisations using Google Workspace or Google Cloud Platform are referred to the separate Google Cloud Privacy Notice for how those services collect and use personal information. "If you’re a member of an organization that uses Google Workspace or Google Cloud Platform, learn how these services collect and use your personal information in the Google Cloud Privacy Notice." - Also in the text (2026-10-08). Google says it uses publicly available information from the web and other public sources to help train machine learning models behind products such as Google Translate, Gemini Apps and Cloud AI. "We use publicly available information online or from other public sources to help train new machine learning models and build foundational technologies that power various Google products such as Google Translate, Gemini Apps, and Cloud AI capabilities." ## Live (updated 2026-10-09 10:14 UTC) - Right now: up, HTTP 404, 14 ms, checked 2026-10-09 10:14 UTC (get on `https://generativelanguage.googleapis.com/v1beta`) - Uptime 24h 100.0% (28 probes) · 30 days 100.0% (28 probes) · p50 17 ms · p95 45 ms - Always current: https://www.anchorterminal.com/api/v1/live/gemini-live.json ## Probe metrics Not measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score. ## Prices | Item | Price | Unit | Note | | --- | --- | --- | --- | | gemini-3.8-live audio input | $0.005 | per minute of audio | $3.00 per 1M audio tokens, charged while the API is listening | | gemini-3.8-live audio output | $0.018 | per minute of audio | $12.00 per 1M audio tokens | | gemini-3.8-live text input | $0.75 | per 1M tokens | | | gemini-3.8-live text output | $4.50 | per 1M tokens | includes thinking tokens and transcription text | | Google Search grounding | $14 | per 1,000 requests | after 5,000 free search queries a month shared across Gemini 3.x models | Across all listings: https://www.anchorterminal.com/prices/index.md ## Strengths - `gemini-3.8-live` went generally available on 15 September 2026 with asynchronous function calling as the default and three response scheduling modes. - Ephemeral tokens can be single use, expire in 30 minutes by default and be locked to a model and session configuration. - Prices are public per million tokens with per-minute equivalents, $0.005 a minute of audio in and $0.018 a minute of audio out. - Session resumption handles, a GoAway message with `timeLeft` and sliding-window context compression are documented for long sessions. - Free tier on the Live models with no billing account, and paid-tier content isn't used to improve Google products per the pricing page. ## Weaknesses - The WebSocket guide authenticates with the API key as a `key` query parameter, and ephemeral tokens as an `access_token` query parameter. - The status page at aistudio.google.com/status renders in the browser only, so no incident history could be read, and no SLA was found for the Developer API. - No machine-readable contract for the WebSocket messages was found. The Discovery document types only the setup and token schemas. - The capabilities, best practices and API reference pages still say the Live API is in preview, and the docs give both 70 and 99 supported languages. - No telephony. Phone calls need a partner such as Voximplant, LiveKit or Pipecat, and concurrent session limits are shown only inside AI Studio. ## Before you call it (notes for agents) 1. Enable `sessionResumption` and keep the newest handle. Connections end after about 10 minutes, and handles stay valid for 2 hours. 2. Set `contextWindowCompression` with a sliding window. Without it audio sessions stop at 15 minutes and audio with video at 2 minutes, and every turn re-bills the whole context. 3. On `gemini-3.8-live` function calls are non-blocking by default. Set `behavior: BLOCKING` if the model must wait for the tool response. 4. Send 16 kHz 16-bit PCM in 20 to 40 ms chunks and discard buffered playback when `interrupted` is true. 5. Keep the API key on a server and send it through the SDK. Give browsers an ephemeral token from `POST /v1beta/auth_tokens`, locked with `liveConnectConstraints`. ## Connect Install: ```bash pip install google-genai # or: npm i @google/genai ``` First request: ```bash curl -X POST "https://generativelanguage.googleapis.com/v1beta/auth_tokens" \ -H "x-goog-api-key: $GEMINI_API_KEY" -H "Content-Type: application/json" \ -d '{"uses": 1, "liveConnectConstraints": {"model": "models/gemini-3.8-live", "config": {"sessionResumption": {}, "responseModalities": ["AUDIO"]}}}' ``` Through letme (picks today, calling later): https://letme.dev/gemini-live. letme answers with the pick and how to call it direct; calling through letme (one key, the vendor's own price) comes later. How it works: https://www.anchorterminal.com/letme/index.md ## Similar tools Ranked by shared capabilities, then score. Same-category tools with no shared capability key are listed last. | Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown | | --- | --- | --- | --- | --- | --- | --- | | Retell AI API + MCP | B | 69.1 | 187 | voice.agent, voice.speech-to-speech, voice.tools | no | https://www.anchorterminal.com/tools/retell-ai.md | | Vapi API + MCP | B | 63.5 | 354 | voice.agent, voice.speech-to-speech, voice.tools | no | https://www.anchorterminal.com/tools/vapi.md | | Ultravox Realtime API | C | 58.5 | 519 | voice.agent, voice.speech-to-speech, voice.tools | no | https://www.anchorterminal.com/tools/ultravox.md | | Hume EVI (Empathic Voice Interface) | C | 56.7 | 564 | voice.agent, voice.speech-to-speech, voice.tools | no | https://www.anchorterminal.com/tools/hume-evi.md | | Bolna API + MCP | D | 52.6 | 649 | voice.agent, voice.speech-to-speech, voice.tools | no | https://www.anchorterminal.com/tools/bolna.md | | ElevenLabs Agents API + MCP | BB | 71.3 | 125 | voice.agent, voice.tools | no | https://www.anchorterminal.com/tools/elevenlabs-agents.md | ## Panel reviews (0) Reviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): . Desk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md ## Notable - `gemini-3.8-live` and `gemini-3.8-live-extended-thinking` went generally available on 15 September 2026 (source: ) - `gemini-3.1-flash-live-preview` and `gemini-2.5-flash-native-audio-preview-12-2025` have an earliest shutdown date of 17 November 2026, with `gemini-3.8-live` named as the replacement (source: ) - Billing compounds. Each turn is charged for all tokens in the session context window, audio accumulates at about 25 tokens a second, and transcription adds text output tokens (source: ) - Proactive audio is permanently on in the 3.8 Live models, so input tokens are charged the whole time the API is listening (source: ) - If a session resumption handle is generated, conversation state including audio and video is kept for up to 24 hours. Zero retention needs `SessionResumptionConfig` left unset (source: ) - Prompts, context and output are kept 55 days for abuse monitoring, and Google Search grounding stores them 30 days with no way to turn that off (source: ) - Partner integrations listed for WebRTC and telephony are LiveKit, Pipecat, Fishjam, Vision Agents, Voximplant, Agora and Firebase AI Logic (source: ) - Google publishes a `gemini-live-api-dev` agent skill and a docs MCP server with `gemini_search_docs` and `gemini_get_doc` (source: ) ## Compare - [Bland AI API + MCP vs Gemini Live API](https://www.anchorterminal.com/compare/bland-ai-vs-gemini-live.md): B 63.8 vs C 57.1 - [Bolna API + MCP vs Gemini Live API](https://www.anchorterminal.com/compare/bolna-vs-gemini-live.md): D 52.6 vs C 57.1 - [Deepgram Voice Agent API vs Gemini Live API](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-gemini-live.md): B 68.1 vs C 57.1 - [ElevenLabs Agents API + MCP vs Gemini Live API](https://www.anchorterminal.com/compare/elevenlabs-agents-vs-gemini-live.md): BB 71.3 vs C 57.1 - [Gemini Live API vs Hume EVI (Empathic Voice Interface)](https://www.anchorterminal.com/compare/gemini-live-vs-hume-evi.md): C 57.1 vs C 56.7 - [Gemini Live API vs Retell AI API + MCP](https://www.anchorterminal.com/compare/gemini-live-vs-retell-ai.md): C 57.1 vs B 69.1 - [Gemini Live API vs Synthflow API + MCP](https://www.anchorterminal.com/compare/gemini-live-vs-synthflow.md): C 57.1 vs D 51.1 - [Gemini Live API vs Ultravox Realtime API](https://www.anchorterminal.com/compare/gemini-live-vs-ultravox.md): C 57.1 vs C 58.5 - [Gemini Live API vs Vapi API + MCP](https://www.anchorterminal.com/compare/gemini-live-vs-vapi.md): C 57.1 vs B 63.5 - [Gemini Live API vs Vocily AI](https://www.anchorterminal.com/compare/gemini-live-vs-vocily.md): C 57.1 vs D 53.8 - [Gemini Live API vs Vogent API](https://www.anchorterminal.com/compare/gemini-live-vs-vogent.md): C 57.1 vs D 47.1 ## Verify this listing For the vendor. The badge or a plain link to this page verifies the listing, from a page on google.com or ai.google.dev or one of their subdomains, or the README of github.com/google-gemini/gemini-live-api-examples. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{"slug": "gemini-live", "url": "…"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify HTML badge: ```html Gemini Live API on Anchor Terminal ``` Markdown badge, for a README: ```markdown [![Gemini Live API on Anchor Terminal](https://www.anchorterminal.com/badges/gemini-live.svg)](https://www.anchorterminal.com/tools/gemini-live) ``` Plain link: ```html Gemini Live API on Anchor Terminal ``` ## Share this listing For the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say Gemini Live API is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score. - Dark: https://www.anchorterminal.com/assets/share/gemini-live-dark.png - Light: https://www.anchorterminal.com/assets/share/gemini-live-light.png