{ "data": { "a": { "slug": "gemini-live", "name": "Gemini Live API", "vendor": "Google", "vendorUrl": "https://ai.google.dev", "kind": "http-api", "category": "voice-agents", "summary": "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.", "url": "https://www.anchorterminal.com/tools/gemini-live", "markdownUrl": "https://www.anchorterminal.com/tools/gemini-live.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/gemini-live.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/gemini-live.json", "repo": "https://github.com/google-gemini/gemini-live-api-examples", "license": "Proprietary service under the Gemini API Additional Terms of Service. The Python and JavaScript SDKs are Apache-2.0", "transports": [ "http" ], "remoteUrl": "https://generativelanguage.googleapis.com/v1beta", "packages": [ { "registry": "pypi", "name": "google-genai" }, { "registry": "npm", "name": "@google/genai" } ], "auth": "api-key", "authNotes": "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", "pricingNotes": "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).", "priceSummary": "$14 / 1k req", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the Live API docs, the pricing page or the billing guide (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": 29486957, "pypiWeekly": 34128301, "asOf": "2026-10-08" }, "docsUrl": "https://ai.google.dev/gemini-api/docs/live-api", "llmsTxt": "https://ai.google.dev/gemini-api/docs/llms.txt", "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" ], "lastRelease": "2026-09-15", "graded": true, "anchor": { "graded": true, "score": 57.1, "grade": "C", "agentReady": false, "rank": 560, "ranked": true, "rankOf": 842, "categoryRank": 7, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 69, "maintenance": 83, "payments": 40, "reliability": 41, "schema": 66, "security": 48, "transparency": 72 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "verdict": "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.", "bestFor": "Teams building their own voice or vision assistant on a single speech-to-speech model with function calling and Search grounding, who can run a backend for tokens and audio transport.", "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." ], "agentNotes": [ "Enable `sessionResumption` and keep the newest handle. Connections end after about 10 minutes, and handles stay valid for 2 hours.", "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.", "On `gemini-3.8-live` function calls are non-blocking by default. Set `behavior: BLOCKING` if the model must wait for the tool response.", "Send 16 kHz 16-bit PCM in 20 to 40 ms chunks and discard buffered playback when `interrupted` is true.", "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`." ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 57.1 } ], "editorialScores": { "ergonomics": 69, "maintenance": 83, "payments": 40, "reliability": 41, "schema": 66, "security": 48, "transparency": 55 }, "provenanceScore": 89 }, "connect": { "install": "pip install google-genai # or: npm i @google/genai", "http": "curl -X POST \"https://generativelanguage.googleapis.com/v1beta/auth_tokens\" \\\n -H \"x-goog-api-key: $GEMINI_API_KEY\" -H \"Content-Type: application/json\" \\\n -d '{\"uses\": 1, \"liveConnectConstraints\": {\"model\": \"models/gemini-3.8-live\", \"config\": {\"sessionResumption\": {}, \"responseModalities\": [\"AUDIO\"]}}}'" }, "letme": { "capability": "https://letme.dev/voice.agent", "tool": "https://letme.dev/gemini-live" }, "sameCompany": [ "gemini-api", "gemini-embedding", "vertex-ai-tuning", "google-model-armor", "google-imagen", "google-veo", "google-lyria", "google-speech-to-text", "google-adk", "google-secret-manager", "google-weather-api", "chrome-devtools-mcp", "google-maps-platform", "google-cloud-translation", "google-calendar-api", "firebase-cloud-messaging", "google-drive-api", "gemini-cli", "google-search-console", "google-ads-api", "google-forms", "google-sheets-api", "gmail-api" ], "area": "voice", "unitPrices": [ { "item": "gemini-3.8-live audio input", "unit": "audio-minute", "usd": 0.005, "note": "$3.00 per 1M audio tokens, charged while the API is listening" }, { "item": "gemini-3.8-live audio output", "unit": "audio-minute", "usd": 0.018, "note": "$12.00 per 1M audio tokens" }, { "item": "gemini-3.8-live text input", "unit": "1m-tokens", "usd": 0.75 }, { "item": "gemini-3.8-live text output", "unit": "1m-tokens", "usd": 4.5, "note": "includes thinking tokens and transcription text" }, { "item": "Google Search grounding", "unit": "1k-requests", "usd": 14, "note": "after 5,000 free search queries a month shared across Gemini 3.x models" } ], "provenance": { "legalEntity": "Google LLC", "domain": "google.com", "domainRegistered": "1997-09-15", "endpointOnVendorDomain": true, "terms": "https://ai.google.dev/gemini-api/terms", "privacy": "https://policies.google.com/privacy", "statusPage": "https://aistudio.google.com/status", "changelog": "https://ai.google.dev/gemini-api/docs/changelog", "securityTxt": "valid", "checked": "2026-10-08", "notes": [ "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." ], "score": 89 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/gemini-live.json", "live": { "slug": "gemini-live", "probe": { "target": "https://generativelanguage.googleapis.com/v1beta", "method": "get", "lastAt": "2026-10-09T10:42:44.067853492Z", "lastOk": true, "lastStatus": 404, "lastMs": 17, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 25, "p95ms24h": 49, "samples24h": 33, "samples30d": 33, "days": [ { "date": "2026-10-09", "probes": 33, "ok": 33 } ] }, "updatedAt": "2026-10-09T10:42:44.067853492Z" } }, "answer": "Gemini Live API scores 57.1 (C) on agent readiness against Vocily AI's 53.8 (D), and leads in 4 of 7 scored categories. Vocily AI leads on schema \u0026 documentation and agent ergonomics.", "b": { "slug": "vocily", "name": "Vocily AI", "vendor": "Vocily AI Private Limited", "vendorUrl": "https://vocily.ai", "kind": "http-api", "category": "voice-agents", "summary": "Vocily AI is a hosted voice-agent platform from Bengaluru for phone calls, WhatsApp and website voice and chat, aimed at Indian languages. Its REST API builds and publishes agents, places outbound calls and reads back transcripts, recordings and costs.", "url": "https://www.anchorterminal.com/tools/vocily", "markdownUrl": "https://www.anchorterminal.com/tools/vocily.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/vocily.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/vocily.json", "license": "Proprietary service under Vocily's terms of service. No open-source code or published package was found", "transports": [ "http" ], "remoteUrl": "https://api.vocily.ai", "packages": [], "auth": "api-key", "authNotes": "A Bearer API key (`vk_...`) created in the dashboard under Developers, API Keys, shown once and revocable there. A key is bound to one workspace and reaches the whole public API for it. Billing, team members, account settings and key management answer 403 to any key. Keys have no scopes to configure, although the error table names an `agents:publish` permission for making a version live. Webhooks are signed with HMAC-SHA256 and a timestamp, with two signatures sent during a secret rotation. Access is self-serve after an email-verified signup.", "pricing": "usage", "pricingNotes": "Prepaid wallet with no monthly fee, billed in rupees or US dollars as chosen at signup, each with its own price list. Voice starts at ₹3.10 or $0.041 a connected minute (speech-to-text, model, voice and a $0.03 platform fee), and telephony is free on your own Plivo or VoBiz account or $0.004 a minute in 30-second pulses on a rented number. Chat is charged per model reply from $0.001. A new organisation gets ₹200 or $2 of credit with no card. Ten concurrent calls are included and a pack of two more is $8 a month (https://vocily.ai/pricing).", "priceSummary": "$8 / mo", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs, the OpenAPI file or the pricing page (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://docs.vocily.ai", "llmsTxt": "https://docs.vocily.ai/llms.txt", "openapi": "https://docs.vocily.ai/developers/openapi.json", "capabilities": [ "voice.agent", "voice.pipeline", "voice.tools", "voice.telephony" ], "tags": [ "hosted", "india", "openapi", "llms-txt", "webhooks", "pipeline", "telephony", "whatsapp", "prepaid", "new" ], "lastRelease": "2026-09-30", "graded": true, "anchor": { "graded": true, "score": 53.8, "grade": "D", "agentReady": false, "rank": 625, "ranked": true, "rankOf": 842, "categoryRank": 9, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 84, "maintenance": 61, "payments": 40, "reliability": 40, "schema": 90, "security": 46, "transparency": 47 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": -5, "negativeNotes": [ "2026-09-23 and 2026-09-25, -3. Two releases removed fields and routes under `/v1` with no notice period, including `tools` on the agent body, `call_type`, `?skip=` and `?offset=`, and the `/widgets` collection routes. The 23 September note says there is no window in which both shapes work. The API reference says fields are never removed or renamed within a version. Documented the same day with migration tables, so the deduction is reduced (https://docs.vocily.ai/developers/changes.md)", "2026-10-08, -2. The developer page on the marketing site lists Fern-generated Python and TypeScript SDKs, an MCP server, API key routes with rotation, webhook endpoint routes, `POST /v1/agents/{id}/chat` and events such as `transcript.ready`. The docs and the OpenAPI file have none of these, keys and webhook endpoints are dashboard-only, and no package was found on npm or PyPI (https://vocily.ai/platform/api-tools and https://docs.vocily.ai/developers/api-reference.md)" ], "verdict": "The REST API is documented in detail for a product a few months old, with an OpenAPI 3.1 file, required idempotency keys on calls, a Retry-After header on 429 and signed webhooks. No status page, SLA, SDK or security programme was found, and two releases in September 2026 removed fields under `/v1` on the day they were announced.", "bestFor": "Indian-language phone agents where a backend builds agents, places outbound calls and reads results over REST, with prepaid rupee billing.", "strengths": [ "OpenAPI 3.1 file with 54 operations, plus llms.txt and a Markdown copy of every docs page", "`POST /v1/calls` requires an `Idempotency-Key`, and a retry returns the original call", "429 responses carry `Retry-After` and `X-RateLimit` headers, with a published limit of 300 requests a minute per key", "Webhooks are signed with HMAC-SHA256 and a timestamp, with a five-minute replay window", "Every component price is public in rupees and US dollars, and signup credit needs no card" ], "weaknesses": [ "No status page, incident history or SLA was found", "Fields and routes were removed under `/v1` on 23 and 25 September 2026 on the day of the announcement", "The marketing site lists SDKs, an MCP server and key management endpoints that the docs don't have", "No security.txt, disclosure policy, bug bounty or certification was found", "The terms and privacy policy name no legal entity, sub-processor or retention period" ], "agentNotes": [ "Send a fresh UUID in `Idempotency-Key` on every `POST /v1/calls`. The API refuses the request without it", "Pass a `from_number` the workspace holds. The shared Test Number returns 403 from the API", "Publish a version and make it live before placing a call, or the call returns 409 `agent_not_published`", "Branch on `detail.code`, falling back to the top-level `code`. A 429 body is flat, so read `Retry-After`", "Read `currency` on every call and chat record. Costs are in rupees or dollars depending on the organisation" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 53.8 } ], "editorialScores": { "ergonomics": 84, "maintenance": 61, "payments": 40, "reliability": 40, "schema": 90, "security": 46, "transparency": 34 }, "provenanceScore": 59 }, "connect": { "http": "curl https://api.vocily.ai/v1/agents \\\n -H \"Authorization: Bearer vk_your_key_here\"" }, "letme": { "capability": "https://letme.dev/voice.agent", "tool": "https://letme.dev/vocily" }, "area": "voice", "unitPrices": [ { "item": "Voice, lowest-priced configuration", "unit": "call-minute", "usd": 0.041, "note": "Soniox, GPT-5 Nano, Vocily voice and the $0.03 platform fee. ₹3.10 for a rupee organisation. Telephony extra on a rented number" }, { "item": "Telephony on a number rented from Vocily", "unit": "call-minute", "usd": 0.004, "note": "billed in 30-second pulses, doubled while a transfer is connected. Free on your own carrier account" }, { "item": "Web chat or WhatsApp AI reply, GPT-5 Nano", "unit": "message", "usd": 0.001, "note": "per model reply, up to $0.02 on GPT-5.6 Terra" }, { "item": "WhatsApp utility template, platform fee", "unit": "message", "usd": 0.0004, "note": "Meta's own charges are paid to Meta separately" }, { "item": "Capacity pack, two more concurrent calls", "unit": "month", "usd": 8, "note": "ten concurrent calls are included at no monthly fee" }, { "item": "Rented Indian phone number", "unit": "month", "usd": 5, "note": "₹499 for a rupee organisation" } ], "provenance": { "legalEntity": "VOCILY AI PRIVATE LIMITED", "domain": "vocily.ai", "domainRegistered": "2026-07-12", "domainNote": "RDAP for vocily.ai gives a registration date of 2026-07-12 and VOCILY AI PRIVATE LIMITED as registrant. vocily.com was registered on 2026-01-27 through Squarespace Domains with no registrant shown, and it redirects to vocily.ai. app.vocily.com, which the site links, redirects to app.vocily.ai.", "endpointOnVendorDomain": true, "terms": "https://vocily.ai/terms", "privacy": "https://vocily.ai/privacy", "statusPage": "", "changelog": "https://docs.vocily.ai/developers/changes", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The terms (last updated 10 June 2026) and the privacy policy (last updated 3 September 2026) refer only to Vocily and name no legal entity, address or governing law. The site footer says Vocily AI, Bengaluru, India. The legal name comes from the registrant field of the vocily.ai domain record.", "The website, the docs (docs.vocily.ai), the API (api.vocily.ai) and the app (app.vocily.ai) are all on vocily.ai. https://vocily.com answers 307 to https://vocily.ai/ and https://app.vocily.com answers 308 to https://app.vocily.ai/.", "No status page was found. status.vocily.ai doesn't resolve and neither the site nor the docs link one.", "https://vocily.ai/.well-known/security.txt and https://vocily.ai/security.txt return 404. The only contact given in the terms and privacy policy is founder@vocily.ai.", "The terms still describe the service as possibly in beta or pre-launch and say paid plans may be introduced later, while the pricing page lists live prices." ], "score": 59 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/vocily.json", "live": { "slug": "vocily", "probe": { "target": "https://api.vocily.ai", "method": "get", "lastAt": "2026-10-09T10:43:01.377514296Z", "lastOk": true, "lastStatus": 200, "lastMs": 559, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 571, "p95ms24h": 640, "samples24h": 184, "samples30d": 184, "days": [ { "date": "2026-10-08", "probes": 70, "ok": 70 }, { "date": "2026-10-09", "probes": 114, "ok": 114 } ] }, "pages": [ { "url": "https://docs.vocily.ai/developers/changes", "kind": "changelog", "status": 200, "checkedAt": "2026-10-08T18:19:44.077645596Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "e943bd4b4dc3" }, { "url": "https://vocily.ai/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-08T18:25:39.585046142Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "056eb2694b97" }, { "url": "https://vocily.ai/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-08T18:25:42.88538991Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "80f0002ad16a" }, { "url": "https://vocily.ai/terms", "kind": "terms", "status": 200, "checkedAt": "2026-10-08T18:25:43.61244357Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "b94cd0abe1e3" } ], "updatedAt": "2026-10-09T10:43:01.377514296Z" } }, "facts": [ { "a": "HTTP API", "b": "HTTP API", "name": "Kind" }, { "a": "Google", "b": "Vocily AI Private Limited", "name": "Vendor" }, { "a": "https://generativelanguage.googleapis.com/v1beta", "b": "https://api.vocily.ai", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "name": "Transports" }, { "a": "API key", "b": "API key", "name": "Auth" }, { "a": "Freemium", "b": "Pay per use", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary service under the Gemini API Additional Terms of Service. The Python and JavaScript SDKs are Apache-2.0", "b": "Proprietary service under Vocily's terms of service. No open-source code or published package was found", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-09-15", "b": "2026-09-30", "name": "Last release" }, { "a": "2026-04-28", "b": "2026-06-10", "name": "Terms last updated" }, { "a": "2026-10-01", "b": "2026-09-03", "name": "Privacy policy last updated" }, { "a": "yes", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "yes", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "yes", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "29.5M npm/wk, 34.1M PyPI/wk", "b": "none", "name": "Popularity" } ], "faq": [ { "answer": "Gemini Live API scores 57.1 (C) on agent readiness against Vocily AI's 53.8 (D), and leads in 4 of 7 scored categories. Vocily AI leads on schema \u0026 documentation and agent ergonomics.", "question": "Which is better for AI agents, Gemini Live API or Vocily AI?" }, { "answer": "Both need an API key.", "question": "Do Gemini Live API and Vocily AI need an API key?" }, { "answer": "Yes. Gemini Live API has a hosted endpoint at https://generativelanguage.googleapis.com/v1beta and Vocily AI at https://api.vocily.ai.", "question": "Can an agent call Gemini Live API and Vocily AI without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Maintenance \u0026 community, 83 against 61", "Transparency \u0026 trust, 72 against 47" ], "also": [ "No incidents deducted, where Vocily AI loses 5 points for them" ], "goodFor": "Teams building their own voice or vision assistant on a single speech-to-speech model with function calling and Search grounding, who can run a backend for tokens and audio transport.", "slug": "gemini-live", "watchFor": "The WebSocket guide authenticates with the API key as a `key` query parameter, and ephemeral tokens as an `access_token` query parameter." }, { "aheadOn": [ "Schema \u0026 documentation, 90 against 66", "Agent ergonomics, 84 against 69" ], "also": null, "goodFor": "Indian-language phone agents where a backend builds agents, places outbound calls and reads results over REST, with prepaid rupee billing.", "slug": "vocily", "watchFor": "No status page, incident history or SLA was found" } ], "job": { "capability": "voice.agent", "name": "Voice agent" }, "others": [ { "json": "https://www.anchorterminal.com/compare/bland-ai-vs-gemini-live.json", "title": "Bland AI API + MCP vs Gemini Live API", "url": "https://www.anchorterminal.com/compare/bland-ai-vs-gemini-live" }, { "json": "https://www.anchorterminal.com/compare/bland-ai-vs-vocily.json", "title": "Bland AI API + MCP vs Vocily AI", "url": "https://www.anchorterminal.com/compare/bland-ai-vs-vocily" }, { "json": "https://www.anchorterminal.com/compare/bolna-vs-gemini-live.json", "title": "Bolna API + MCP vs Gemini Live API", "url": "https://www.anchorterminal.com/compare/bolna-vs-gemini-live" }, { "json": "https://www.anchorterminal.com/compare/bolna-vs-vocily.json", "title": "Bolna API + MCP vs Vocily AI", "url": "https://www.anchorterminal.com/compare/bolna-vs-vocily" }, { "json": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-gemini-live.json", "title": "Deepgram Voice Agent API vs Gemini Live API", "url": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-gemini-live" }, { "json": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-vocily.json", "title": "Deepgram Voice Agent API vs Vocily AI", "url": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-vocily" }, { "json": "https://www.anchorterminal.com/compare/elevenlabs-agents-vs-gemini-live.json", "title": "ElevenLabs Agents API + MCP vs Gemini Live API", "url": "https://www.anchorterminal.com/compare/elevenlabs-agents-vs-gemini-live" }, { "json": "https://www.anchorterminal.com/compare/elevenlabs-agents-vs-vocily.json", "title": "ElevenLabs Agents API + MCP vs Vocily AI", "url": "https://www.anchorterminal.com/compare/elevenlabs-agents-vs-vocily" }, { "json": "https://www.anchorterminal.com/compare/gemini-live-vs-hume-evi.json", "title": "Gemini Live API vs Hume EVI (Empathic Voice Interface)", "url": "https://www.anchorterminal.com/compare/gemini-live-vs-hume-evi" }, { "json": "https://www.anchorterminal.com/compare/gemini-live-vs-retell-ai.json", "title": "Gemini Live API vs Retell AI API + MCP", "url": "https://www.anchorterminal.com/compare/gemini-live-vs-retell-ai" }, { "json": "https://www.anchorterminal.com/compare/gemini-live-vs-synthflow.json", "title": "Gemini Live API vs Synthflow API + MCP", "url": "https://www.anchorterminal.com/compare/gemini-live-vs-synthflow" }, { "json": "https://www.anchorterminal.com/compare/gemini-live-vs-ultravox.json", "title": "Gemini Live API vs Ultravox Realtime API", "url": "https://www.anchorterminal.com/compare/gemini-live-vs-ultravox" }, { "json": "https://www.anchorterminal.com/compare/gemini-live-vs-vapi.json", "title": "Gemini Live API vs Vapi API + MCP", "url": "https://www.anchorterminal.com/compare/gemini-live-vs-vapi" }, { "json": "https://www.anchorterminal.com/compare/gemini-live-vs-vogent.json", "title": "Gemini Live API vs Vogent API", "url": "https://www.anchorterminal.com/compare/gemini-live-vs-vogent" }, { "json": "https://www.anchorterminal.com/compare/hume-evi-vs-vocily.json", "title": "Hume EVI (Empathic Voice Interface) vs Vocily AI", "url": "https://www.anchorterminal.com/compare/hume-evi-vs-vocily" }, { "json": "https://www.anchorterminal.com/compare/retell-ai-vs-vocily.json", "title": "Retell AI API + MCP vs Vocily AI", "url": "https://www.anchorterminal.com/compare/retell-ai-vs-vocily" }, { "json": "https://www.anchorterminal.com/compare/synthflow-vs-vocily.json", "title": "Synthflow API + MCP vs Vocily AI", "url": "https://www.anchorterminal.com/compare/synthflow-vs-vocily" }, { "json": "https://www.anchorterminal.com/compare/ultravox-vs-vocily.json", "title": "Ultravox Realtime API vs Vocily AI", "url": "https://www.anchorterminal.com/compare/ultravox-vs-vocily" }, { "json": "https://www.anchorterminal.com/compare/vapi-vs-vocily.json", "title": "Vapi API + MCP vs Vocily AI", "url": "https://www.anchorterminal.com/compare/vapi-vs-vocily" }, { "json": "https://www.anchorterminal.com/compare/vocily-vs-vogent.json", "title": "Vocily AI vs Vogent API", "url": "https://www.anchorterminal.com/compare/vocily-vs-vogent" } ], "scores": [ { "by": 1, "edge": "gemini-live", "gemini-live": 41, "key": "reliability", "name": "Reliability", "vocily": 40, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 24, "edge": "vocily", "gemini-live": 66, "key": "schema", "name": "Schema \u0026 documentation", "vocily": 90, "weight": 13 }, { "by": 15, "edge": "vocily", "gemini-live": 69, "key": "ergonomics", "name": "Agent ergonomics", "vocily": 84, "weight": 13 }, { "by": 2, "edge": "gemini-live", "gemini-live": 48, "key": "security", "name": "Security \u0026 auth", "vocily": 46, "weight": 14 }, { "by": 0, "edge": "", "gemini-live": 40, "key": "payments", "name": "Payments \u0026 pricing", "vocily": 40, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 22, "edge": "gemini-live", "gemini-live": 83, "key": "maintenance", "name": "Maintenance \u0026 community", "vocily": 61, "weight": 7 }, { "by": 25, "edge": "gemini-live", "gemini-live": 72, "key": "transparency", "name": "Transparency \u0026 trust", "vocily": 47, "weight": 7 } ], "summary": "Gemini Live API scores 57.1 (C) on agent readiness against Vocily AI's 53.8 (D), and leads in 4 of 7 scored categories. Vocily AI leads on schema \u0026 documentation and agent ergonomics. Both do voice agent.", "verdicts": { "gemini-live": "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.", "vocily": "The REST API is documented in detail for a product a few months old, with an OpenAPI 3.1 file, required idempotency keys on calls, a Retry-After header on 429 and signed webhooks. No status page, SLA, SDK or security programme was found, and two releases in September 2026 removed fields under `/v1` on the day they were announced." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/gemini-live-vs-vocily", "json": "https://www.anchorterminal.com/compare/gemini-live-vs-vocily.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/gemini-live-vs-vocily.md", "slim": "https://www.anchorterminal.com/compare/gemini-live-vs-vocily.min.md" }, "markdown": "Gemini Live API scores 57.1 (C) on agent readiness against Vocily AI's 53.8 (D), and leads in 4 of 7 scored categories. Vocily AI leads on schema \u0026 documentation and agent ergonomics. Both do voice agent.\n\n- Gemini Live API: grade C, 57.1/100, rank #560 of 842. Markdown https://www.anchorterminal.com/tools/gemini-live.md · JSON https://www.anchorterminal.com/api/v1/tools/gemini-live.json\n- Vocily AI: grade D, 53.8/100, rank #625 of 842. Markdown https://www.anchorterminal.com/tools/vocily.md · JSON https://www.anchorterminal.com/api/v1/tools/vocily.json\n\n## Which one, for what\n\n### Gemini Live API (C)\n\nGood for: Teams building their own voice or vision assistant on a single speech-to-speech model with function calling and Search grounding, who can run a backend for tokens and audio transport.\n\nAhead on:\n- Maintenance \u0026 community, 83 against 61\n- Transparency \u0026 trust, 72 against 47\n\nAlso in its favour:\n- No incidents deducted, where Vocily AI loses 5 points for them\n\nWatch for: The WebSocket guide authenticates with the API key as a `key` query parameter, and ephemeral tokens as an `access_token` query parameter.\n\n### Vocily AI (D)\n\nGood for: Indian-language phone agents where a backend builds agents, places outbound calls and reads results over REST, with prepaid rupee billing.\n\nAhead on:\n- Schema \u0026 documentation, 90 against 66\n- Agent ergonomics, 84 against 69\n\nWatch for: No status page, incident history or SLA was found\n\n\n## Score by category\n\n| Category | Weight | Gemini Live API | Vocily AI | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 41 | 40 | Gemini Live API +1 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 66 | 90 | Vocily AI +24 |\n| Agent ergonomics | 13% (16.2 this run) | 69 | 84 | Vocily AI +15 |\n| Security \u0026 auth | 14% (17.5 this run) | 48 | 46 | Gemini Live API +2 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 40 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 83 | 61 | Gemini Live API +22 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 72 | 47 | Gemini Live API +25 |\n| Negative events | ≤15 | 0 | -5 | |\n| **Total** | | **57.1 · C** | **53.8 · D** | |\n\n## Facts side by side\n\n| Fact | Gemini Live API | Vocily AI |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Google | Vocily AI Private Limited |\n| Hosted endpoint | `https://generativelanguage.googleapis.com/v1beta` | `https://api.vocily.ai` |\n| Transports | HTTP | HTTP |\n| Auth | API key | API key |\n| Pricing | Freemium | Pay per use |\n| x402 | no | no |\n| Licence | Proprietary service under the Gemini API Additional Terms of Service. The Python and JavaScript SDKs are Apache-2.0 | Proprietary service under Vocily's terms of service. No open-source code or published package was found |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-09-15 | 2026-09-30 |\n| Terms last updated | 2026-04-28 | 2026-06-10 |\n| Privacy policy last updated | 2026-10-01 | 2026-09-03 |\n| Customer content may train models | yes | not found in the text |\n| Terms restrict automated access | yes | not found in the text |\n| Terms restrict benchmarking | yes | not found in the text |\n| Terms or service can change without notice | not found in the text | not found in the text |\n| Arbitration or class-action waiver | not found in the text | not found in the text |\n| Popularity | 29.5M npm/wk, 34.1M PyPI/wk | none |\n\n## Verdicts\n\n**Gemini Live API.** 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.\n\n**Vocily AI.** The REST API is documented in detail for a product a few months old, with an OpenAPI 3.1 file, required idempotency keys on calls, a Retry-After header on 429 and signed webhooks. No status page, SLA, SDK or security programme was found, and two releases in September 2026 removed fields under `/v1` on the day they were announced.\n\n## Before you call either\n\n### Gemini Live API\n\n1. Enable `sessionResumption` and keep the newest handle. Connections end after about 10 minutes, and handles stay valid for 2 hours.\n2. 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.\n3. On `gemini-3.8-live` function calls are non-blocking by default. Set `behavior: BLOCKING` if the model must wait for the tool response.\n4. Send 16 kHz 16-bit PCM in 20 to 40 ms chunks and discard buffered playback when `interrupted` is true.\n5. 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`.\n\n### Vocily AI\n\n1. Send a fresh UUID in `Idempotency-Key` on every `POST /v1/calls`. The API refuses the request without it\n2. Pass a `from_number` the workspace holds. The shared Test Number returns 403 from the API\n3. Publish a version and make it live before placing a call, or the call returns 409 `agent_not_published`\n4. Branch on `detail.code`, falling back to the top-level `code`. A 429 body is flat, so read `Retry-After`\n5. Read `currency` on every call and chat record. Costs are in rupees or dollars depending on the organisation\n\n## Questions\n\n### Which is better for AI agents, Gemini Live API or Vocily AI?\n\nGemini Live API scores 57.1 (C) on agent readiness against Vocily AI's 53.8 (D), and leads in 4 of 7 scored categories. Vocily AI leads on schema \u0026 documentation and agent ergonomics.\n\n### Do Gemini Live API and Vocily AI need an API key?\n\nBoth need an API key.\n\n### Can an agent call Gemini Live API and Vocily AI without installing anything?\n\nYes. Gemini Live API has a hosted endpoint at https://generativelanguage.googleapis.com/v1beta and Vocily AI at https://api.vocily.ai.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/gemini-live-vs-vocily.json, and with the fewest tokens: https://www.anchorterminal.com/compare/gemini-live-vs-vocily.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"gemini-live\", \"b\": \"vocily\"}`. From a terminal: `anchor compare gemini-live vocily`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/gemini-live.json and https://www.anchorterminal.com/api/v1/tools/vocily.json\n\n## Other comparisons with Gemini Live API or Vocily AI\n\n- [Bland AI API + MCP vs Gemini Live API](https://www.anchorterminal.com/compare/bland-ai-vs-gemini-live.md)\n- [Bland AI API + MCP vs Vocily AI](https://www.anchorterminal.com/compare/bland-ai-vs-vocily.md)\n- [Bolna API + MCP vs Gemini Live API](https://www.anchorterminal.com/compare/bolna-vs-gemini-live.md)\n- [Bolna API + MCP vs Vocily AI](https://www.anchorterminal.com/compare/bolna-vs-vocily.md)\n- [Deepgram Voice Agent API vs Gemini Live API](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-gemini-live.md)\n- [Deepgram Voice Agent API vs Vocily AI](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-vocily.md)\n- [ElevenLabs Agents API + MCP vs Gemini Live API](https://www.anchorterminal.com/compare/elevenlabs-agents-vs-gemini-live.md)\n- [ElevenLabs Agents API + MCP vs Vocily AI](https://www.anchorterminal.com/compare/elevenlabs-agents-vs-vocily.md)\n- [Gemini Live API vs Hume EVI (Empathic Voice Interface)](https://www.anchorterminal.com/compare/gemini-live-vs-hume-evi.md)\n- [Gemini Live API vs Retell AI API + MCP](https://www.anchorterminal.com/compare/gemini-live-vs-retell-ai.md)\n- [Gemini Live API vs Synthflow API + MCP](https://www.anchorterminal.com/compare/gemini-live-vs-synthflow.md)\n- [Gemini Live API vs Ultravox Realtime API](https://www.anchorterminal.com/compare/gemini-live-vs-ultravox.md)\n- [Gemini Live API vs Vapi API + MCP](https://www.anchorterminal.com/compare/gemini-live-vs-vapi.md)\n- [Gemini Live API vs Vogent API](https://www.anchorterminal.com/compare/gemini-live-vs-vogent.md)\n- [Hume EVI (Empathic Voice Interface) vs Vocily AI](https://www.anchorterminal.com/compare/hume-evi-vs-vocily.md)\n- [Retell AI API + MCP vs Vocily AI](https://www.anchorterminal.com/compare/retell-ai-vs-vocily.md)\n- [Synthflow API + MCP vs Vocily AI](https://www.anchorterminal.com/compare/synthflow-vs-vocily.md)\n- [Ultravox Realtime API vs Vocily AI](https://www.anchorterminal.com/compare/ultravox-vs-vocily.md)\n- [Vapi API + MCP vs Vocily AI](https://www.anchorterminal.com/compare/vapi-vs-vocily.md)\n- [Vocily AI vs Vogent API](https://www.anchorterminal.com/compare/vocily-vs-vogent.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-09", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Gemini Live API vs Vocily AI", "url": "" } ], "description": "Gemini Live API scores 57.1 (C) on agent readiness against Vocily AI's 53.8 (D), and leads in 4 of 7 scored categories. Vocily AI leads on schema \u0026 documentation and agent ergonomics. Both do voice agent. Category scores, facts, verdicts and agent notes side by side.", "facts": [ "Gemini Live API C 57.1", "Vocily AI D 53.8", "scores" ], "h1": "Gemini Live API vs Vocily AI", "image": "https://www.anchorterminal.com/assets/og/compare-gemini-live-vs-vocily.png", "path": "/compare/gemini-live-vs-vocily", "published": "2026-10-01", "section": "tools", "title": "Gemini Live API vs Vocily AI for AI agents, C 57.1 vs D 53.8", "toc": null, "updated": "2026-10-09", "url": "https://www.anchorterminal.com/compare/gemini-live-vs-vocily" }, "tokens": { "markdown": 2400, "slim": 680 }, "version": 1 }