{ "data": { "a": { "slug": "deepgram-voice-agent", "name": "Deepgram Voice Agent API", "vendor": "Deepgram", "vendorUrl": "https://deepgram.com", "kind": "http-api", "category": "voice-agents", "summary": "One WebSocket that runs Deepgram STT (Flux or Nova-3), a managed or bring-your-own LLM and Deepgram or third-party TTS, with turn-taking, barge-in and function calling.", "url": "https://www.anchorterminal.com/tools/deepgram-voice-agent", "markdownUrl": "https://www.anchorterminal.com/tools/deepgram-voice-agent.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/deepgram-voice-agent.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/deepgram-voice-agent.json", "dns": "deepgram-voice-agent.grade.anchorterminal.com", "repo": "https://github.com/deepgram/deepgram-python-sdk", "license": "MIT (SDKs)", "transports": [ "http", "streamable-http", "stdio", "sse" ], "remoteUrl": "https://agent.deepgram.com/v1/agent", "packages": [ { "registry": "npm", "name": "@deepgram/sdk" }, { "registry": "pypi", "name": "deepgram-sdk" }, { "registry": "pypi", "name": "deepctl" } ], "auth": "api-key", "authNotes": "`Authorization: Token \u003ckey\u003e` header on REST and WebSocket calls. Short-lived JWTs (30-second TTL) from the token endpoint for browsers. The `dg` CLI MCP server uses `dg login` credentials or `DEEPGRAM_API_KEY`. The docs MCP needs no key. BYO LLM and TTS providers take their own keys in the `endpoint.headers` of the Settings message.", "pricing": "usage", "pricingNotes": "Billed per minute of WebSocket connection time. Standard $0.075 a minute pay as you go ($0.068 Growth), Standard with your own TTS $0.065 ($0.051 Growth), your own LLM $0.065 ($0.059 Growth), your own LLM and TTS $0.050 ($0.041 Growth). Advanced tier (larger LLMs such as GPT-5 or Claude Sonnet) $0.163 ($0.146 Growth), or $0.122 with your own TTS ($0.110 Growth). $200 free credit with no card. Carrier costs are extra (https://deepgram.com/pricing).", "priceSummary": "Pay per use", "where": "both", "x402": { "level": "no", "evidence": "No x402 or machine payment in the docs or pricing. Card or prepaid credits only (checked 2026-09-30).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 468, "npmWeekly": 1123798, "pypiWeekly": 805026, "asOf": "2026-09-30" }, "docsUrl": "https://developers.deepgram.com/docs/voice-agent", "llmsTxt": "https://developers.deepgram.com/llms.txt", "capabilities": [ "voice.agent", "voice.pipeline", "voice.tools" ], "tags": [ "hosted", "no-card", "closed-source", "python", "typescript", "llms-txt", "mcp", "streaming", "pipeline", "enterprise", "self-hosted" ], "lastRelease": "2026-10-28", "graded": true, "anchor": { "graded": true, "score": 72.2, "grade": "BB", "agentReady": true, "rank": 136, "ranked": true, "rankOf": 1510, "categoryRank": 3, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 67, "maintenance": 85, "payments": 40, "reliability": 75, "schema": 90, "security": 71, "transparency": 78 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": 0, "verdict": "$0.075 a minute all in on Standard, $0.050 with your own LLM and TTS, and $200 of credit with no card. Every status incident since August was partial. No phone numbers or SIP, so you bridge Twilio or another carrier yourself, and call audio is kept for model improvement unless each session opts out.", "bestFor": "Developers who already run telephony (Twilio, Amazon Connect, Genesys, AudioCodes) and want a cheap managed pipeline with their choice of LLM.", "strengths": [ "$0.075 a minute all in on Standard, $0.050 with your own LLM and TTS, $200 of credit with no card", "AsyncAPI description of the agent socket plus a public OpenAPI file", "Role-based API keys with expiry and 30-second browser tokens", "SDKs in Python, JavaScript, Java, Go, .NET and Rust, the Python and JavaScript ones released on 28 October 2026", "Function-call hold that waits for a confirmed user turn before irreversible tools run" ], "weaknesses": [ "No phone numbers or SIP, so you bridge Twilio or another carrier yourself", "Nineteen status incidents from 3 August to 29 October, each partial, one of them failing Voice Agent sessions at one datacenter on 29 October", "Call audio is kept for model improvement unless `mip_opt_out` is set, and the 2021 privacy policy doesn't mention it", "No SLA terms on self-serve plans", "Sessions end at 2 hours" ], "agentNotes": [ "Set `mip_opt_out` in the Settings message to keep call audio out of training", "Use the function-call hold for anything irreversible, since replies can start before the user's turn is confirmed", "Back off exponentially on 429, a pay-as-you-go project gets 45 concurrent sockets", "Pin the LLM version, an unpinned Gemini route failed for 1.5 hours on 21 July 2026", "Mint browser tokens with `ttl_seconds`, not `ttl`, or they expire after 30 seconds" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 72.2 } ], "editorialScores": { "ergonomics": 67, "maintenance": 85, "payments": 40, "reliability": 75, "schema": 90, "security": 71, "transparency": 60 }, "provenanceScore": 95, "checked": { "categories": { "ergonomics": "2026-11-01", "maintenance": "2026-11-01", "payments": "2026-11-01", "reliability": "2026-11-01", "schema": "2026-11-01", "security": "2026-11-01", "transparency": "2026-11-01" }, "last": "2026-11-01", "lastMoved": "2026-11-01", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 } }, "connect": { "http": "curl https://agent.deepgram.com/v1/agent/settings/think/models \\\n -H \"Authorization: Token $DEEPGRAM_API_KEY\"", "claudeCode": "claude mcp add deepgram-docs --transport http https://api.dx.deepgram.com/kapa/mcp", "config": { "mcpServers": { "deepgram": { "args": [ "mcp" ], "command": "dg", "env": { "DEEPGRAM_API_KEY": "${DEEPGRAM_API_KEY}" } } } } }, "letme": { "capability": "https://letme.dev/voice.agent", "tool": "https://letme.dev/deepgram-voice-agent" }, "sameCompany": [ "deepgram-stt", "deepgram-tts" ], "area": "voice", "unitPrices": [ { "item": "Standard", "unit": "call-minute", "usd": 0.075, "note": "pay as you go, Deepgram STT, managed LLM and TTS included, carrier extra" }, { "item": "Standard with own TTS", "unit": "call-minute", "usd": 0.065 }, { "item": "Own LLM", "unit": "call-minute", "usd": 0.065, "note": "Deepgram STT and TTS, your own LLM" }, { "item": "Own LLM and TTS", "unit": "call-minute", "usd": 0.05, "note": "STT and orchestration only" }, { "item": "Advanced", "unit": "call-minute", "usd": 0.163, "note": "larger LLMs, all-in except carrier" }, { "item": "Advanced with own TTS", "unit": "call-minute", "usd": 0.122 } ], "provenance": { "legalEntity": "Deepgram, Inc.", "domain": "deepgram.com", "domainRegistered": "2016-01-28", "endpointOnVendorDomain": true, "terms": "https://deepgram.com/terms", "privacy": "https://deepgram.com/privacy", "statusPage": "https://status.deepgram.com", "changelog": "https://developers.deepgram.com/changelog", "securityTxt": "valid", "checked": "2026-11-01", "notes": [ "https://deepgram.com/.well-known/security.txt answered 200 on 1 November 2026 with Contact mailto:security@deepgram.com and Expires 2027-09-30T00:00:00.000Z. It was not found on 30 September." ], "score": 95 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/deepgram-voice-agent.json", "live": { "slug": "deepgram-voice-agent", "probe": { "target": "https://agent.deepgram.com/v1/agent", "method": "get", "lastAt": "2026-11-07T19:22:02.978370869Z", "lastOk": true, "lastStatus": 404, "lastMs": 417, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 401, "p95ms24h": 500, "samples24h": 238, "samples30d": 7920, "days": [ { "date": "2026-10-07", "probes": 272, "ok": 272 }, { "date": "2026-10-08", "probes": 268, "ok": 268 }, { "date": "2026-10-09", "probes": 250, "ok": 250 }, { "date": "2026-10-10", "probes": 247, "ok": 247 }, { "date": "2026-10-11", "probes": 247, "ok": 247 }, { "date": "2026-10-12", "probes": 247, "ok": 247 }, { "date": "2026-10-13", "probes": 248, "ok": 248 }, { "date": "2026-10-14", "probes": 249, "ok": 249 }, { "date": "2026-10-15", "probes": 253, "ok": 253 }, { "date": "2026-10-16", "probes": 252, "ok": 252 }, { "date": "2026-10-17", "probes": 253, "ok": 253 }, { "date": "2026-10-18", "probes": 256, "ok": 256 }, { "date": "2026-10-19", "probes": 255, "ok": 255 }, { "date": "2026-10-20", "probes": 252, "ok": 252 }, { "date": "2026-10-21", "probes": 253, "ok": 253 }, { "date": "2026-10-22", "probes": 253, "ok": 253 }, { "date": "2026-10-23", "probes": 248, "ok": 248 }, { "date": "2026-10-24", "probes": 251, "ok": 251 }, { "date": "2026-10-25", "probes": 250, "ok": 250 }, { "date": "2026-10-26", "probes": 252, "ok": 252 }, { "date": "2026-10-27", "probes": 249, "ok": 249 }, { "date": "2026-10-28", "probes": 251, "ok": 251 }, { "date": "2026-10-29", "probes": 248, "ok": 248 }, { "date": "2026-10-30", "probes": 249, "ok": 249 }, { "date": "2026-10-31", "probes": 251, "ok": 251 }, { "date": "2026-11-01", "probes": 249, "ok": 249 }, { "date": "2026-11-02", "probes": 250, "ok": 250 }, { "date": "2026-11-03", "probes": 248, "ok": 248 }, { "date": "2026-11-04", "probes": 246, "ok": 246 }, { "date": "2026-11-05", "probes": 185, "ok": 185 }, { "date": "2026-11-06", "probes": 241, "ok": 241 }, { "date": "2026-11-07", "probes": 197, "ok": 197 } ] }, "vendorStatus": { "page": "https://status.deepgram.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-07T19:21:42.451802859Z" }, "versions": [ { "registry": "github", "name": "deepgram/deepgram-python-sdk", "version": "v7.17.0", "released": "2026-11-04", "seenAt": "2026-11-06T23:20:24.910394663Z" }, { "registry": "npm", "name": "@deepgram/sdk", "version": "5.18.0", "seenAt": "2026-11-06T23:20:22.644100995Z" }, { "registry": "pypi", "name": "deepctl", "version": "0.4.0", "released": "2026-10-20", "seenAt": "2026-11-06T23:20:22.978980994Z" }, { "registry": "pypi", "name": "deepgram-sdk", "version": "7.17.0", "released": "2026-11-04", "seenAt": "2026-11-06T23:20:22.869617831Z" } ], "githubStars": 479, "npmWeekly": 1352542, "pypiWeekly": 917348, "securityTxt": { "url": "https://deepgram.com/.well-known/security.txt", "state": "valid", "expires": "2027-09-30T00:00:00.000Z", "checkedAt": "2026-11-07T16:01:56.590929452Z" }, "llmsTxt": { "url": "https://developers.deepgram.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:19.56139377Z" }, "domain": { "domain": "deepgram.com", "registered": "2016-01-28", "source": "https://rdap.verisign.com/com/v1/domain/deepgram.com", "checkedAt": "2026-11-01T14:09:32.822991287Z" }, "github": { "repo": "deepgram/deepgram-python-sdk", "checkedAt": "2026-11-02T08:43:22.258450881Z", "stars": 476, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-30T19:47:20Z", "openIssues": 14, "openPRs": 8, "issuesOpened90d": 24, "issuesClosed90d": 30, "prsMerged90d": 38, "ci": { "branch": "main", "runs": 50, "success": 50, "failure": 0, "other": 0, "latest": "success", "latestAt": "2026-10-30T17:09:16Z" }, "replies": { "sampled": 25, "unanswered": 12, "medianDays": 4.6 } }, "updatedAt": "2026-11-07T19:22:02.978370869Z" } }, "answer": "Deepgram Voice Agent API scores 72.2 (BB) on agent readiness against Inworld Realtime API's 60.1 (C), and leads in 5 of 7 scored categories.", "b": { "slug": "inworld-realtime", "name": "Inworld Realtime API", "vendor": "Inworld AI", "vendorUrl": "https://inworld.ai", "kind": "http-api", "category": "voice-agents", "summary": "Inworld's Realtime API runs spoken conversations over WebSocket or WebRTC, chaining Inworld STT, an LLM chosen by the developer and Inworld TTS, with turn detection, interruptions and tool calling. It follows OpenAI's Realtime protocol.", "url": "https://www.anchorterminal.com/tools/inworld-realtime", "markdownUrl": "https://www.anchorterminal.com/tools/inworld-realtime.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/inworld-realtime.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/inworld-realtime.json", "dns": "inworld-realtime.grade.anchorterminal.com", "transports": [ "websocket", "http" ], "packages": [ { "registry": "npm", "name": "@inworld/cli" } ], "auth": "api-key", "authNotes": "Servers send `Authorization: Basic` with the Base64 `key_id:secret` credential. Browsers send `Authorization: Bearer` with a session token minted server side. The `key` query parameter in the WebSocket URL is a session ID, not a secret.", "pricing": "usage", "pricingNotes": "No per-minute or per-session price. A session is billed as its STT ($0.10 to $0.15 an hour), its LLM tokens at the model's rate and its TTS characters (TTS-2 from $25 per million on the free plan). Segments already sent to TTS are billed after an interruption.", "priceSummary": "Pay per use", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs, llms.txt or pricing page (checked 2026-11-06). Plans and credits are bought in the Portal.", "endpoints": [] }, "toolCount": 0, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://docs.inworld.ai/realtime/overview", "llmsTxt": "https://docs.inworld.ai/llms.txt", "capabilities": [ "voice.agent", "voice.pipeline", "voice.tools", "voice.telephony" ], "tags": [ "hosted", "usage", "free-tier", "closed-source", "llms-txt", "streaming", "websocket", "webrtc", "openai-compatible", "enterprise" ], "lastRelease": "2026-10-16", "graded": true, "anchor": { "graded": true, "score": 60.1, "grade": "C", "agentReady": false, "rank": 671, "ranked": true, "rankOf": 1510, "categoryRank": 12, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 68, "maintenance": 71, "payments": 40, "reliability": 62, "schema": 60, "security": 58, "transparency": 63 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": 0, "verdict": "Inworld's Realtime API speaks OpenAI's Realtime protocol over WebSocket or WebRTC, with a choice of LLM, client-side tools and dated release notes. Cost is the sum of STT, LLM and TTS usage with no per-minute price, there is no machine-readable event schema, and status history couldn't be read.", "bestFor": "Teams moving off OpenAI's Realtime API who want a choice of LLM and Inworld voices.", "strengths": [ "Follows OpenAI's Realtime events, with a migration guide that changes only the URL, key and a few defaults", "Dated release notes name affected clients and required actions for each compatibility change", "A choice of LLM through Inworld's router, with prompt caching on Anthropic models", "Concurrent sessions from 10 on the free plan to 1,000 on Growth", "Zero data retention covers session content from the Developer plan up" ], "weaknesses": [ "No per-minute price. A session's cost depends on STT, LLM tokens and TTS characters, and interrupted segments are still billed", "No AsyncAPI or other machine-readable schema for the socket events", "Status history couldn't be read, and an SLA exists only for Enterprise", "The 21 July 2026 release changed response and item shapes for existing clients", "Zero data retention doesn't cover requests routed to third-party LLM providers" ], "agentNotes": [ "Set the auto follow-up off if your client sends its own `response.create` after a tool result, or replies double", "Read `response.done` usage as an estimate and mute input audio when nobody speaks, since STT bills every second sent", "Use `response.speak` for fixed greetings, which skips the LLM", "Treat `unsupported_field` errors as warnings and keep the session open", "Mint browser session tokens on your server and never ship the Basic credential to a client" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 60.1 } ], "editorialScores": { "ergonomics": 68, "maintenance": 71, "payments": 40, "reliability": 62, "schema": 60, "security": 58, "transparency": 51 }, "provenanceScore": 75, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "npm install -g @inworld/cli" }, "letme": { "capability": "https://letme.dev/voice.agent", "tool": "https://letme.dev/inworld-realtime" }, "sameCompany": [ "inworld-stt", "inworld-tts", "inworld-voice-cloning" ], "area": "voice", "unitPrices": [ { "item": "Speech recognition in a session", "unit": "audio-minute", "usd": 0.0025, "note": "STT-1 at $0.15 an hour On-Demand, $0.10 on paid plans" }, { "item": "Agent speech, TTS-2", "unit": "1m-chars", "usd": 25, "note": "free On-Demand plan; lower on paid plans" } ], "provenance": { "legalEntity": "Theai, Inc. dba Inworld AI", "domain": "inworld.ai", "domainRegistered": "", "endpointOnVendorDomain": true, "terms": "https://inworld.ai/terms", "privacy": "https://inworld.ai/privacy", "statusPage": "https://status.inworld.ai", "changelog": "https://docs.inworld.ai/release-notes/realtime", "securityTxt": "none", "checked": "2026-11-06", "notes": [ "The Terms of Service (effective 11 June 2025) are an agreement with Theai, Inc. dba Inworld AI under California law, with courts in Santa Clara. The Privacy Notice (last updated 18 January 2026) names Theai, Inc.", "inworld.ai/.well-known/security.txt returns 404. The security page links a vulnerability report form.", "status.inworld.ai runs the open-source issue-status app, which draws incidents from GitHub issues in inworld-ai/inworld-issue-status. Its history wasn't read, because GitHub's robots.txt couldn't be read from our environment.", "inworld.ai's robots.txt allows Claude agents on the paths read and sets `Content-Signal: ai-train=no, search=yes, ai-input=no`. docs.inworld.ai has no such signal.", "The domain's registration date wasn't established, because the RDAP lookup failed.", "firstReleased is left empty. The public Realtime release notes start on 21 July 2026 and no launch date was found." ], "score": 75 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/inworld-realtime.json", "live": { "slug": "inworld-realtime", "vendorStatus": { "page": "https://status.inworld.ai", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-11-07T04:47:57.03709454Z" }, "versions": [ { "registry": "npm", "name": "@inworld/cli", "version": "1.5.0", "seenAt": "2026-11-06T23:35:04.551623033Z" } ], "npmWeekly": 290, "securityTxt": { "url": "https://inworld.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:11.794771951Z" }, "llmsTxt": { "url": "https://docs.inworld.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:46.028273902Z" }, "pages": [ { "url": "https://docs.inworld.ai/release-notes/realtime", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:06:42.218731652Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "9ae0f1f05b69" }, { "url": "https://inworld.ai/privacy", "kind": "privacy", "status": 304, "checkedAt": "2026-11-07T14:11:39.031139211Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "99dc39a9de92" }, { "url": "https://inworld.ai/terms", "kind": "terms", "status": 304, "checkedAt": "2026-11-07T14:11:41.181276356Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "777d881cbf9b" } ], "updatedAt": "2026-11-07T16:01:11.794771951Z" } }, "edges": [ { "by": 30, "category": "schema", "leads": "deepgram-voice-agent", "name": "Schema \u0026 documentation", "reasons": { "a": "Public OpenAPI and an AsyncAPI file that describes the agent socket messages (25). llms.txt with a Markdown copy of each page, and a keyless docs MCP server (10). Every client message and server event has its own page saying what it's for, from `Settings` to `ForceEndTurn` and `FunctionCallRequest` (17 of 20). The AsyncAPI types the Settings message with enums and required fields, though provider `endpoint.headers` are free-form (13 of 15). Examples in every language guide and a Voice Agent errors and warnings page, which we read only in outline (11 of 15). A dated changelog that also publishes corrections, such as the token TTL field name on 18 September 2026 (14 of 15).", "b": "No AsyncAPI or other machine-readable file for the socket, and the spec paths redirect (0). llms.txt, Markdown twins and a docs MCP server (10). The overview, OpenAI migration guide, `providerData` reference and the billing page's account of how a session is counted say what to use when (16 of 20). The reference lists every client and server event with field types and required marks, as text rather than a schema (12 of 15). JavaScript and Python example projects and an error event with `type`, `code` and `param`, without a list of codes (9 of 15). Dated release notes with affected clients and required actions, but no API version beyond `/v1` (13 of 15). Total 60." }, "scores": { "a": 90, "b": 60 } }, { "by": 15, "category": "transparency", "leads": "deepgram-voice-agent", "name": "Transparency \u0026 trust", "reasons": { "a": "The service is closed with clear terms, and the official SDKs are MIT (15 of 30, read as deepgram-stt and deepgram-tts are). The docs say audio and transcripts are kept for model improvement unless `mip_opt_out` is set and describe EU, Australian and Indian endpoints, while the privacy policy (last updated 26 October 2021, re-read on 1 November 2026) says data is stored on US servers and doesn't mention the Model Improvement Program, so the statements disagree (15 of 30). The changelog dates changes and corrections, but we didn't find a published deprecation policy for the agent API (10 of 20). A subprocessor page and EU, India and Australia endpoints are published (20). 15 + 15 + 10 + 20 = 60. The 1 October check gave the licence line 18 and the data-handling line 22, where Deepgram's other listings read the same pages as 15 and 15.", "b": "Closed service with clear terms naming Theai, Inc. dba Inworld AI (15). The ZDR page says what a session keeps and that third-party LLM requests aren't covered, but the terms and privacy notice disagree on training (12 of 30). Release notes flag potentially breaking changes with the clients affected and what to do, without stating a notice period (14 of 20). US headquarters with EU and India residency on Enterprise, and no sub-processor list in the docs, while sessions may route to third-party LLM providers (10 of 20). Total 51." }, "scores": { "a": 78, "b": 63 } }, { "by": 14, "category": "maintenance", "leads": "deepgram-voice-agent", "name": "Maintenance \u0026 community", "reasons": { "a": "Changelog entries to 27 October 2026 and the Python and JavaScript SDKs released on 28 October (Python 7.16.0, JavaScript 5.17.0), both adding Voice Agent Think Live messages (30). 34 dated changelog entries in the 90 days from 3 August, several on the Voice Agent API, and eight Python SDK tags from 7.9.0 on 14 September to 7.16.0 on 28 October (20). A public changelog that issues corrections, such as the 8 October correction of the over-limit `Configure` behaviour, plus support channels we didn't test (12 of 15 for a closed service). Official SDKs current in Python, JavaScript, Java, Go, .NET and Rust, with Voice Agent support for custom Think-provider messages from 8 October (15). MIT SDKs with current releases (8 of 10). 30 + 20 + 12 + 15 + 8 = 85.", "b": "Release note of 16 October 2026 (`cache_transcript`), 21 days ago (30). Three dated Realtime entries in the 90 days from 8 August, on 14 September, 23 September and 16 October (20). Discord and support@inworld.ai, with no evidence of answers read (8 of 15). Works with OpenAI's Realtime clients and the CLI is current at 1.5.0, but there is no Inworld Realtime SDK (8 of 15). CLI on npm under MIT, CI not read (5 of 10). Total 71." }, "scores": { "a": 85, "b": 71 } }, { "by": 13, "category": "reliability", "leads": "deepgram-voice-agent", "name": "Reliability", "reasons": { "a": "Statuspage at status.deepgram.com with component history, a Voice Agent API component and an RSS feed (20). Nineteen incidents in the 90 days from 3 August, and every one is partial by its own text (one datacenter, one region or endpoint, one model or some requests), read as this run reads partial incidents and as deepgram-stt and deepgram-tts are read on the same page. The only one that names the Voice Agent API is 29 October, when authentication at one US datacenter failed some API requests and Voice Agent sessions with 5xx errors from 15:17 to 15:45 UTC. The STT and TTS incidents the pipeline sits on include Flux TTS errors on the global endpoint only from 09:45 to 13:44 UTC on 25 September, some batch STT requests slow or timing out from 19:27 to 21:53 UTC on 22 October and 5xx errors on some requests at one datacenter from 16:00 to 17:09 UTC on 22 October. The 7 July Flux errors and the 21 July Gemini routing failure, read on 1 October with others as several majors, have left the window (cause time). Minor only (20). Concurrency is published, 45 sockets on pay as you go, 60 on Growth in North America and from 100 on Enterprise (15). Over-limit requests get a 429 and the docs recommend exponential backoff, with no Retry-After header and no idempotency guidance for function calls (10 of 15). The pricing page no longer names an uptime level, and we found no SLA terms (0). The Voice Agent API is generally available (10). 20 + 20 + 15 + 10 + 0 + 10 = 75.", "b": "Hosted reading of the checklist. status.inworld.ai is a public status page (20), with history we couldn't read, as on inworld-tts (5). Concurrent sessions are published per plan, 10 on On-Demand up to 1,000 on Growth (15). The rate limits page gives exponential backoff with jitter and Retry-After on longer windows, and sessions emit `rate_limits.updated`, with nothing on reconnecting a dropped session (12 of 15). An SLA appears only in the Enterprise column, with no terms (0). No preview or beta label on the Realtime API (10). 20 + 5 + 15 + 12 + 0 + 10 = 62." }, "scores": { "a": 75, "b": 62 } }, { "by": 13, "category": "security", "leads": "deepgram-voice-agent", "name": "Security \u0026 auth", "reasons": { "a": "API keys carry an owner, admin or member role, can be set to expire, can be created through the API and can be tagged, and browsers get 30-second JWTs from the token endpoint (30). Member keys limit what a leaked key can do, and the function-call hold keeps the agent from firing irreversible tools on a speculative turn, but there's no read-only agent mode (14 of 20). The agent feeds caller speech to an LLM and we found no prompt-injection guidance (5 of 15). Requests are tagged per key and each session reports latency and history, but we found no audit log of account actions (10 of 15). The compliance page states SOC 2 Type 1 and Type 2, HIPAA and PCI. deepgram.com now serves a valid security.txt (Contact security@deepgram.com, Expires 30 September 2027), not found on 30 September. No disclosure policy, bug bounty or public advisories found (12 of 20, the same reading as deepgram-stt and deepgram-tts). 30 + 14 + 5 + 10 + 12 = 71.", "b": "Workspace API keys sent as Basic credentials, deleted to revoke, with separate keys per environment advised. The CLI mints read-only keys unless `--write` is given, but write toggles cover only the Voice and Router APIs, so no key is limited to one product. Browsers use short-lived tokens minted server side. Session IDs, not secrets, go in the URL (25 of 30). Tools run in the client, so the developer approves side effects, with no approval step in the API (10 of 20). The agent listens to callers and passes their speech to an LLM, and no prompt-injection guidance was found (5 of 15). Usage per key and a Performance page with errors and throttling (8 of 15). SOC 2 Type II and HIPAA claimed and a vulnerability report form, with no security.txt or bug bounty, per the 4 November reading (10 of 20). Total 58. Zero data retention covers session content from the Developer plan up, but not requests routed to third-party LLM providers." }, "scores": { "a": 71, "b": 58 } } ], "facts": [ { "a": "HTTP API", "b": "HTTP API", "name": "Kind" }, { "a": "Deepgram", "b": "Inworld AI", "name": "Vendor" }, { "a": "https://agent.deepgram.com/v1/agent", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP, Streamable HTTP, stdio, SSE (legacy)", "b": "websocket, HTTP", "name": "Transports" }, { "a": "API key", "b": "API key", "name": "Auth" }, { "a": "Pay per use", "b": "Pay per use", "name": "Pricing" }, { "a": "not published", "b": "$25 per 1M characters", "name": "Price for voice agents" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "MIT (SDKs)", "b": "none", "name": "Licence" }, { "a": "none", "b": "0", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-28", "b": "2026-10-16", "name": "Last release" }, { "a": "2026-08-06", "b": "2025-06-11", "name": "Terms last updated" }, { "a": "2021-10-26", "b": "2026-01-18", "name": "Privacy policy last updated" }, { "a": "yes, with an opt-out", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "yes", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "yes", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "yes", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "468 stars, 1.1M npm/wk, 805k PyPI/wk", "b": "none", "name": "Popularity" }, { "a": "3/5 (2)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Deepgram Voice Agent API scores 72.2 (BB) on agent readiness against Inworld Realtime API's 60.1 (C), and leads in 5 of 7 scored categories.", "question": "Which is better for AI agents, Deepgram Voice Agent API or Inworld Realtime API?" }, { "answer": "Both need an API key.", "question": "Do Deepgram Voice Agent API and Inworld Realtime API need an API key?" }, { "answer": "Deepgram Voice Agent API has a hosted endpoint at https://agent.deepgram.com/v1/agent. No hosted endpoint is listed for Inworld Realtime API.", "question": "Can an agent call Deepgram Voice Agent API and Inworld Realtime API without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 75 against 62", "Schema \u0026 documentation, 90 against 60", "Security \u0026 auth, 71 against 58", "Maintenance \u0026 community, 85 against 71", "Transparency \u0026 trust, 78 against 63" ], "also": [ "Agent-ready, a grade of BB or better", "A hosted endpoint, with nothing to install", "Runs on your own machine", "Free to start without a card" ], "goodFor": "Developers who already run telephony (Twilio, Amazon Connect, Genesys, AudioCodes) and want a cheap managed pipeline with their choice of LLM.", "slug": "deepgram-voice-agent", "watchFor": "No phone numbers or SIP, so you bridge Twilio or another carrier yourself" }, { "aheadOn": null, "also": null, "goodFor": "Teams moving off OpenAI's Realtime API who want a choice of LLM and Inworld voices.", "slug": "inworld-realtime", "watchFor": "No per-minute price. A session's cost depends on STT, LLM tokens and TTS characters, and interrupted segments are still billed" } ], "history": { "deepgram-voice-agent": [ { "causes": [ "time" ], "date": "2026-11-01", "delta": 4, "from": 68.2, "fromGrade": "B", "to": 72.2, "toGrade": "BB" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.1, "from": 68.1, "fromGrade": "B", "to": 68.2, "toGrade": "B" }, { "causes": [ "method" ], "date": "2026-10-08", "delta": -0.3, "from": 68.4, "fromGrade": "B", "to": 68.1, "toGrade": "B" } ], "inworld-realtime": null }, "job": { "capability": "voice.agent", "name": "Voice agents" }, "others": [ { "json": "https://www.anchorterminal.com/compare/amazon-nova-sonic-vs-deepgram-voice-agent.json", "title": "Amazon Nova 2 Sonic vs Deepgram Voice Agent API", "url": "https://www.anchorterminal.com/compare/amazon-nova-sonic-vs-deepgram-voice-agent" }, { "json": "https://www.anchorterminal.com/compare/amazon-nova-sonic-vs-inworld-realtime.json", "title": "Amazon Nova 2 Sonic vs Inworld Realtime API", "url": "https://www.anchorterminal.com/compare/amazon-nova-sonic-vs-inworld-realtime" }, { "json": "https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-deepgram-voice-agent.json", "title": "AssemblyAI Voice Agent API vs Deepgram Voice Agent API", "url": "https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-deepgram-voice-agent" }, { "json": "https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-inworld-realtime.json", "title": "AssemblyAI Voice Agent API vs Inworld Realtime API", "url": "https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-inworld-realtime" }, { "json": "https://www.anchorterminal.com/compare/bland-ai-vs-deepgram-voice-agent.json", "title": "Bland AI API + MCP vs Deepgram Voice Agent API", "url": "https://www.anchorterminal.com/compare/bland-ai-vs-deepgram-voice-agent" }, { "json": "https://www.anchorterminal.com/compare/bland-ai-vs-inworld-realtime.json", "title": "Bland AI API + MCP vs Inworld Realtime API", "url": "https://www.anchorterminal.com/compare/bland-ai-vs-inworld-realtime" }, { "json": "https://www.anchorterminal.com/compare/bolna-vs-deepgram-voice-agent.json", "title": "Bolna API + MCP vs Deepgram Voice Agent API", "url": "https://www.anchorterminal.com/compare/bolna-vs-deepgram-voice-agent" }, { "json": "https://www.anchorterminal.com/compare/bolna-vs-inworld-realtime.json", "title": "Bolna API + MCP vs Inworld Realtime API", "url": "https://www.anchorterminal.com/compare/bolna-vs-inworld-realtime" }, { "json": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-elevenlabs-agents.json", "title": "Deepgram Voice Agent API vs ElevenLabs Agents API + MCP", "url": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-elevenlabs-agents" }, { "json": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-fone-me.json", "title": "Deepgram Voice Agent API vs fone.me", "url": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-fone-me" }, { "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-gpt-live.json", "title": "Deepgram Voice Agent API vs GPT-Live", "url": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-gpt-live" }, { "json": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-harmony-ai.json", "title": "Deepgram Voice Agent API vs Harmony.ai", "url": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-harmony-ai" }, { "json": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-hume-evi.json", "title": "Deepgram Voice Agent API vs Hume EVI (Empathic Voice Interface)", "url": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-hume-evi" }, { "json": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-livekit-agents.json", "title": "Deepgram Voice Agent API vs LiveKit Agents", "url": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-livekit-agents" }, { "json": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-openai-realtime.json", "title": "Deepgram Voice Agent API vs OpenAI Realtime API", "url": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-openai-realtime" }, { "json": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-pipecat.json", "title": "Deepgram Voice Agent API vs Pipecat", "url": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-pipecat" }, { "json": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-placecall.json", "title": "Deepgram Voice Agent API vs PlaceCall", "url": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-placecall" }, { "json": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-retell-ai.json", "title": "Deepgram Voice Agent API vs Retell AI API + MCP", "url": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-retell-ai" }, { "json": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-rime-prism.json", "title": "Deepgram Voice Agent API vs Rime Prism", "url": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-rime-prism" }, { "json": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-synthflow.json", "title": "Deepgram Voice Agent API vs Synthflow API + MCP", "url": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-synthflow" }, { "json": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-ultravox.json", "title": "Deepgram Voice Agent API vs Ultravox Realtime API", "url": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-ultravox" }, { "json": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-vaani-voice.json", "title": "Deepgram Voice Agent API vs Vaani Developer Platform", "url": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-vaani-voice" }, { "json": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-vapi.json", "title": "Deepgram Voice Agent API vs Vapi API + MCP", "url": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-vapi" }, { "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/deepgram-voice-agent-vs-vogent.json", "title": "Deepgram Voice Agent API vs Vogent API", "url": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-vogent" }, { "json": "https://www.anchorterminal.com/compare/elevenlabs-agents-vs-inworld-realtime.json", "title": "ElevenLabs Agents API + MCP vs Inworld Realtime API", "url": "https://www.anchorterminal.com/compare/elevenlabs-agents-vs-inworld-realtime" }, { "json": "https://www.anchorterminal.com/compare/fone-me-vs-inworld-realtime.json", "title": "fone.me vs Inworld Realtime API", "url": "https://www.anchorterminal.com/compare/fone-me-vs-inworld-realtime" }, { "json": "https://www.anchorterminal.com/compare/gemini-live-vs-inworld-realtime.json", "title": "Gemini Live API vs Inworld Realtime API", "url": "https://www.anchorterminal.com/compare/gemini-live-vs-inworld-realtime" }, { "json": "https://www.anchorterminal.com/compare/gpt-live-vs-inworld-realtime.json", "title": "GPT-Live vs Inworld Realtime API", "url": "https://www.anchorterminal.com/compare/gpt-live-vs-inworld-realtime" }, { "json": "https://www.anchorterminal.com/compare/harmony-ai-vs-inworld-realtime.json", "title": "Harmony.ai vs Inworld Realtime API", "url": "https://www.anchorterminal.com/compare/harmony-ai-vs-inworld-realtime" }, { "json": "https://www.anchorterminal.com/compare/hume-evi-vs-inworld-realtime.json", "title": "Hume EVI (Empathic Voice Interface) vs Inworld Realtime API", "url": "https://www.anchorterminal.com/compare/hume-evi-vs-inworld-realtime" }, { "json": "https://www.anchorterminal.com/compare/inworld-realtime-vs-livekit-agents.json", "title": "Inworld Realtime API vs LiveKit Agents", "url": "https://www.anchorterminal.com/compare/inworld-realtime-vs-livekit-agents" }, { "json": "https://www.anchorterminal.com/compare/inworld-realtime-vs-openai-realtime.json", "title": "Inworld Realtime API vs OpenAI Realtime API", "url": "https://www.anchorterminal.com/compare/inworld-realtime-vs-openai-realtime" }, { "json": "https://www.anchorterminal.com/compare/inworld-realtime-vs-pipecat.json", "title": "Inworld Realtime API vs Pipecat", "url": "https://www.anchorterminal.com/compare/inworld-realtime-vs-pipecat" }, { "json": "https://www.anchorterminal.com/compare/inworld-realtime-vs-placecall.json", "title": "Inworld Realtime API vs PlaceCall", "url": "https://www.anchorterminal.com/compare/inworld-realtime-vs-placecall" }, { "json": "https://www.anchorterminal.com/compare/inworld-realtime-vs-retell-ai.json", "title": "Inworld Realtime API vs Retell AI API + MCP", "url": "https://www.anchorterminal.com/compare/inworld-realtime-vs-retell-ai" }, { "json": "https://www.anchorterminal.com/compare/inworld-realtime-vs-rime-prism.json", "title": "Inworld Realtime API vs Rime Prism", "url": "https://www.anchorterminal.com/compare/inworld-realtime-vs-rime-prism" }, { "json": "https://www.anchorterminal.com/compare/inworld-realtime-vs-synthflow.json", "title": "Inworld Realtime API vs Synthflow API + MCP", "url": "https://www.anchorterminal.com/compare/inworld-realtime-vs-synthflow" }, { "json": "https://www.anchorterminal.com/compare/inworld-realtime-vs-ultravox.json", "title": "Inworld Realtime API vs Ultravox Realtime API", "url": "https://www.anchorterminal.com/compare/inworld-realtime-vs-ultravox" }, { "json": "https://www.anchorterminal.com/compare/inworld-realtime-vs-vaani-voice.json", "title": "Inworld Realtime API vs Vaani Developer Platform", "url": "https://www.anchorterminal.com/compare/inworld-realtime-vs-vaani-voice" }, { "json": "https://www.anchorterminal.com/compare/inworld-realtime-vs-vapi.json", "title": "Inworld Realtime API vs Vapi API + MCP", "url": "https://www.anchorterminal.com/compare/inworld-realtime-vs-vapi" }, { "json": "https://www.anchorterminal.com/compare/inworld-realtime-vs-vocily.json", "title": "Inworld Realtime API vs Vocily AI", "url": "https://www.anchorterminal.com/compare/inworld-realtime-vs-vocily" }, { "json": "https://www.anchorterminal.com/compare/inworld-realtime-vs-vogent.json", "title": "Inworld Realtime API vs Vogent API", "url": "https://www.anchorterminal.com/compare/inworld-realtime-vs-vogent" }, { "json": "https://www.anchorterminal.com/compare/cuelight-vs-deepgram-voice-agent.json", "title": "CueLight vs Deepgram Voice Agent API", "url": "https://www.anchorterminal.com/compare/cuelight-vs-deepgram-voice-agent" }, { "json": "https://www.anchorterminal.com/compare/cuelight-vs-inworld-realtime.json", "title": "CueLight vs Inworld Realtime API", "url": "https://www.anchorterminal.com/compare/cuelight-vs-inworld-realtime" }, { "json": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-pipecat-phonellm.json", "title": "Deepgram Voice Agent API vs Pipecat PhoneLLM", "url": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-pipecat-phonellm" }, { "json": "https://www.anchorterminal.com/compare/inworld-realtime-vs-pipecat-phonellm.json", "title": "Inworld Realtime API vs Pipecat PhoneLLM", "url": "https://www.anchorterminal.com/compare/inworld-realtime-vs-pipecat-phonellm" } ], "panel": null, "scores": [ { "by": 13, "deepgram-voice-agent": 75, "edge": "deepgram-voice-agent", "inworld-realtime": 62, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 30, "deepgram-voice-agent": 90, "edge": "deepgram-voice-agent", "inworld-realtime": 60, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 1, "deepgram-voice-agent": 67, "edge": "inworld-realtime", "inworld-realtime": 68, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 13, "deepgram-voice-agent": 71, "edge": "deepgram-voice-agent", "inworld-realtime": 58, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 0, "deepgram-voice-agent": 40, "edge": "", "inworld-realtime": 40, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 14, "deepgram-voice-agent": 85, "edge": "deepgram-voice-agent", "inworld-realtime": 71, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 15, "deepgram-voice-agent": 78, "edge": "deepgram-voice-agent", "inworld-realtime": 63, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Deepgram Voice Agent API scores 72.2 (BB) on agent readiness against Inworld Realtime API's 60.1 (C), and leads in 5 of 7 scored categories. Both do voice agents.", "tasks": null, "tutorials": [], "verdicts": { "deepgram-voice-agent": "$0.075 a minute all in on Standard, $0.050 with your own LLM and TTS, and $200 of credit with no card. Every status incident since August was partial. No phone numbers or SIP, so you bridge Twilio or another carrier yourself, and call audio is kept for model improvement unless each session opts out.", "inworld-realtime": "Inworld's Realtime API speaks OpenAI's Realtime protocol over WebSocket or WebRTC, with a choice of LLM, client-side tools and dated release notes. Cost is the sum of STT, LLM and TTS usage with no per-minute price, there is no machine-readable event schema, and status history couldn't be read." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-inworld-realtime", "json": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-inworld-realtime.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-inworld-realtime.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-inworld-realtime.min.md" }, "markdown": "Deepgram Voice Agent API scores 72.2 (BB) on agent readiness against Inworld Realtime API's 60.1 (C), and leads in 5 of 7 scored categories. Both do voice agents.\n\n- Deepgram Voice Agent API: grade BB, 72.2/100, rank #136 of 1510. Markdown https://www.anchorterminal.com/tools/deepgram-voice-agent.md · JSON https://www.anchorterminal.com/api/v1/tools/deepgram-voice-agent.json\n- Inworld Realtime API: grade C, 60.1/100, rank #671 of 1510. Markdown https://www.anchorterminal.com/tools/inworld-realtime.md · JSON https://www.anchorterminal.com/api/v1/tools/inworld-realtime.json\n- Best conversational voice-agent APIs: https://www.anchorterminal.com/best/voice-agents/index.md\n- All 518 voice agents comparisons: https://www.anchorterminal.com/compare/voice-agents/index.md\n\n## Which one, for what\n\n### Deepgram Voice Agent API (BB)\n\nGood for: Developers who already run telephony (Twilio, Amazon Connect, Genesys, AudioCodes) and want a cheap managed pipeline with their choice of LLM.\n\nAhead on:\n- Reliability, 75 against 62\n- Schema \u0026 documentation, 90 against 60\n- Security \u0026 auth, 71 against 58\n- Maintenance \u0026 community, 85 against 71\n- Transparency \u0026 trust, 78 against 63\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- A hosted endpoint, with nothing to install\n- Runs on your own machine\n- Free to start without a card\n\nWatch for: No phone numbers or SIP, so you bridge Twilio or another carrier yourself\n\n### Inworld Realtime API (C)\n\nGood for: Teams moving off OpenAI's Realtime API who want a choice of LLM and Inworld voices.\n\nWatch for: No per-minute price. A session's cost depends on STT, LLM tokens and TTS characters, and interrupted segments are still billed\n\n\n## Why the edge\n\n### Schema \u0026 documentation: Deepgram Voice Agent API +30\n\n- Deepgram Voice Agent API (90): Public OpenAPI and an AsyncAPI file that describes the agent socket messages (25). llms.txt with a Markdown copy of each page, and a keyless docs MCP server (10). Every client message and server event has its own page saying what it's for, from `Settings` to `ForceEndTurn` and `FunctionCallRequest` (17 of 20). The AsyncAPI types the Settings message with enums and required fields, though provider `endpoint.headers` are free-form (13 of 15). Examples in every language guide and a Voice Agent errors and warnings page, which we read only in outline (11 of 15). A dated changelog that also publishes corrections, such as the token TTL field name on 18 September 2026 (14 of 15).\n- Inworld Realtime API (60): No AsyncAPI or other machine-readable file for the socket, and the spec paths redirect (0). llms.txt, Markdown twins and a docs MCP server (10). The overview, OpenAI migration guide, `providerData` reference and the billing page's account of how a session is counted say what to use when (16 of 20). The reference lists every client and server event with field types and required marks, as text rather than a schema (12 of 15). JavaScript and Python example projects and an error event with `type`, `code` and `param`, without a list of codes (9 of 15). Dated release notes with affected clients and required actions, but no API version beyond `/v1` (13 of 15). Total 60.\n\n### Transparency \u0026 trust: Deepgram Voice Agent API +15\n\n- Deepgram Voice Agent API (78): The service is closed with clear terms, and the official SDKs are MIT (15 of 30, read as deepgram-stt and deepgram-tts are). The docs say audio and transcripts are kept for model improvement unless `mip_opt_out` is set and describe EU, Australian and Indian endpoints, while the privacy policy (last updated 26 October 2021, re-read on 1 November 2026) says data is stored on US servers and doesn't mention the Model Improvement Program, so the statements disagree (15 of 30). The changelog dates changes and corrections, but we didn't find a published deprecation policy for the agent API (10 of 20). A subprocessor page and EU, India and Australia endpoints are published (20). 15 + 15 + 10 + 20 = 60. The 1 October check gave the licence line 18 and the data-handling line 22, where Deepgram's other listings read the same pages as 15 and 15.\n- Inworld Realtime API (63): Closed service with clear terms naming Theai, Inc. dba Inworld AI (15). The ZDR page says what a session keeps and that third-party LLM requests aren't covered, but the terms and privacy notice disagree on training (12 of 30). Release notes flag potentially breaking changes with the clients affected and what to do, without stating a notice period (14 of 20). US headquarters with EU and India residency on Enterprise, and no sub-processor list in the docs, while sessions may route to third-party LLM providers (10 of 20). Total 51.\n\n### Maintenance \u0026 community: Deepgram Voice Agent API +14\n\n- Deepgram Voice Agent API (85): Changelog entries to 27 October 2026 and the Python and JavaScript SDKs released on 28 October (Python 7.16.0, JavaScript 5.17.0), both adding Voice Agent Think Live messages (30). 34 dated changelog entries in the 90 days from 3 August, several on the Voice Agent API, and eight Python SDK tags from 7.9.0 on 14 September to 7.16.0 on 28 October (20). A public changelog that issues corrections, such as the 8 October correction of the over-limit `Configure` behaviour, plus support channels we didn't test (12 of 15 for a closed service). Official SDKs current in Python, JavaScript, Java, Go, .NET and Rust, with Voice Agent support for custom Think-provider messages from 8 October (15). MIT SDKs with current releases (8 of 10). 30 + 20 + 12 + 15 + 8 = 85.\n- Inworld Realtime API (71): Release note of 16 October 2026 (`cache_transcript`), 21 days ago (30). Three dated Realtime entries in the 90 days from 8 August, on 14 September, 23 September and 16 October (20). Discord and support@inworld.ai, with no evidence of answers read (8 of 15). Works with OpenAI's Realtime clients and the CLI is current at 1.5.0, but there is no Inworld Realtime SDK (8 of 15). CLI on npm under MIT, CI not read (5 of 10). Total 71.\n\n### Reliability: Deepgram Voice Agent API +13\n\n- Deepgram Voice Agent API (75): Statuspage at status.deepgram.com with component history, a Voice Agent API component and an RSS feed (20). Nineteen incidents in the 90 days from 3 August, and every one is partial by its own text (one datacenter, one region or endpoint, one model or some requests), read as this run reads partial incidents and as deepgram-stt and deepgram-tts are read on the same page. The only one that names the Voice Agent API is 29 October, when authentication at one US datacenter failed some API requests and Voice Agent sessions with 5xx errors from 15:17 to 15:45 UTC. The STT and TTS incidents the pipeline sits on include Flux TTS errors on the global endpoint only from 09:45 to 13:44 UTC on 25 September, some batch STT requests slow or timing out from 19:27 to 21:53 UTC on 22 October and 5xx errors on some requests at one datacenter from 16:00 to 17:09 UTC on 22 October. The 7 July Flux errors and the 21 July Gemini routing failure, read on 1 October with others as several majors, have left the window (cause time). Minor only (20). Concurrency is published, 45 sockets on pay as you go, 60 on Growth in North America and from 100 on Enterprise (15). Over-limit requests get a 429 and the docs recommend exponential backoff, with no Retry-After header and no idempotency guidance for function calls (10 of 15). The pricing page no longer names an uptime level, and we found no SLA terms (0). The Voice Agent API is generally available (10). 20 + 20 + 15 + 10 + 0 + 10 = 75.\n- Inworld Realtime API (62): Hosted reading of the checklist. status.inworld.ai is a public status page (20), with history we couldn't read, as on inworld-tts (5). Concurrent sessions are published per plan, 10 on On-Demand up to 1,000 on Growth (15). The rate limits page gives exponential backoff with jitter and Retry-After on longer windows, and sessions emit `rate_limits.updated`, with nothing on reconnecting a dropped session (12 of 15). An SLA appears only in the Enterprise column, with no terms (0). No preview or beta label on the Realtime API (10). 20 + 5 + 15 + 12 + 0 + 10 = 62.\n\n### Security \u0026 auth: Deepgram Voice Agent API +13\n\n- Deepgram Voice Agent API (71): API keys carry an owner, admin or member role, can be set to expire, can be created through the API and can be tagged, and browsers get 30-second JWTs from the token endpoint (30). Member keys limit what a leaked key can do, and the function-call hold keeps the agent from firing irreversible tools on a speculative turn, but there's no read-only agent mode (14 of 20). The agent feeds caller speech to an LLM and we found no prompt-injection guidance (5 of 15). Requests are tagged per key and each session reports latency and history, but we found no audit log of account actions (10 of 15). The compliance page states SOC 2 Type 1 and Type 2, HIPAA and PCI. deepgram.com now serves a valid security.txt (Contact security@deepgram.com, Expires 30 September 2027), not found on 30 September. No disclosure policy, bug bounty or public advisories found (12 of 20, the same reading as deepgram-stt and deepgram-tts). 30 + 14 + 5 + 10 + 12 = 71.\n- Inworld Realtime API (58): Workspace API keys sent as Basic credentials, deleted to revoke, with separate keys per environment advised. The CLI mints read-only keys unless `--write` is given, but write toggles cover only the Voice and Router APIs, so no key is limited to one product. Browsers use short-lived tokens minted server side. Session IDs, not secrets, go in the URL (25 of 30). Tools run in the client, so the developer approves side effects, with no approval step in the API (10 of 20). The agent listens to callers and passes their speech to an LLM, and no prompt-injection guidance was found (5 of 15). Usage per key and a Performance page with errors and throttling (8 of 15). SOC 2 Type II and HIPAA claimed and a vulnerability report form, with no security.txt or bug bounty, per the 4 November reading (10 of 20). Total 58. Zero data retention covers session content from the Developer plan up, but not requests routed to third-party LLM providers.\n\n## Score by category\n\n| Category | Weight | Deepgram Voice Agent API | Inworld Realtime API | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 75 | 62 | Deepgram Voice Agent API +13 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 90 | 60 | Deepgram Voice Agent API +30 |\n| Agent ergonomics | 13% (16.2 this run) | 67 | 68 | Inworld Realtime API +1 |\n| Security \u0026 auth | 14% (17.5 this run) | 71 | 58 | Deepgram Voice Agent API +13 |\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) | 85 | 71 | Deepgram Voice Agent API +14 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 78 | 63 | Deepgram Voice Agent API +15 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **72.2 · BB** | **60.1 · C** | |\n\n## Facts side by side\n\n| Fact | Deepgram Voice Agent API | Inworld Realtime API |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Deepgram | Inworld AI |\n| Hosted endpoint | `https://agent.deepgram.com/v1/agent` | no (local only) |\n| Transports | HTTP, Streamable HTTP, stdio, SSE (legacy) | websocket, HTTP |\n| Auth | API key | API key |\n| Pricing | Pay per use | Pay per use |\n| Price for voice agents | not published | $25 per 1M characters |\n| x402 | no | no |\n| Licence | MIT (SDKs) | none |\n| Tools exposed | none | 0 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-10-28 | 2026-10-16 |\n| Terms last updated | 2026-08-06 | 2025-06-11 |\n| Privacy policy last updated | 2021-10-26 | 2026-01-18 |\n| Customer content may train models | yes, with an opt-out | not found in the text |\n| Terms restrict automated access | not found in the text | not found in the text |\n| Terms restrict benchmarking | yes | not found in the text |\n| Terms or service can change without notice | yes | not found in the text |\n| Arbitration or class-action waiver | yes | not found in the text |\n| Popularity | 468 stars, 1.1M npm/wk, 805k PyPI/wk | none |\n| Agent reviews | 3/5 (2) | none |\n\n## How the scores have moved\n\n### Deepgram Voice Agent API\n\n- +4.0 on 1 November 2026 (B to BB): time\n- +0.1 on 27 October 2026: checklist\n- -0.3 on 8 October 2026: checklist\n\n### Inworld Realtime API\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Deepgram Voice Agent API.** $0.075 a minute all in on Standard, $0.050 with your own LLM and TTS, and $200 of credit with no card. Every status incident since August was partial. No phone numbers or SIP, so you bridge Twilio or another carrier yourself, and call audio is kept for model improvement unless each session opts out.\n\n**Inworld Realtime API.** Inworld's Realtime API speaks OpenAI's Realtime protocol over WebSocket or WebRTC, with a choice of LLM, client-side tools and dated release notes. Cost is the sum of STT, LLM and TTS usage with no per-minute price, there is no machine-readable event schema, and status history couldn't be read.\n\n## Before you call either\n\n### Deepgram Voice Agent API\n\n1. Set `mip_opt_out` in the Settings message to keep call audio out of training\n2. Use the function-call hold for anything irreversible, since replies can start before the user's turn is confirmed\n3. Back off exponentially on 429, a pay-as-you-go project gets 45 concurrent sockets\n4. Pin the LLM version, an unpinned Gemini route failed for 1.5 hours on 21 July 2026\n5. Mint browser tokens with `ttl_seconds`, not `ttl`, or they expire after 30 seconds\n\n### Inworld Realtime API\n\n1. Set the auto follow-up off if your client sends its own `response.create` after a tool result, or replies double\n2. Read `response.done` usage as an estimate and mute input audio when nobody speaks, since STT bills every second sent\n3. Use `response.speak` for fixed greetings, which skips the LLM\n4. Treat `unsupported_field` errors as warnings and keep the session open\n5. Mint browser session tokens on your server and never ship the Basic credential to a client\n\n## Questions\n\n### Which is better for AI agents, Deepgram Voice Agent API or Inworld Realtime API?\n\nDeepgram Voice Agent API scores 72.2 (BB) on agent readiness against Inworld Realtime API's 60.1 (C), and leads in 5 of 7 scored categories.\n\n### Do Deepgram Voice Agent API and Inworld Realtime API need an API key?\n\nBoth need an API key.\n\n### Can an agent call Deepgram Voice Agent API and Inworld Realtime API without installing anything?\n\nDeepgram Voice Agent API has a hosted endpoint at https://agent.deepgram.com/v1/agent. No hosted endpoint is listed for Inworld Realtime API.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-inworld-realtime.json, and with the fewest tokens: https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-inworld-realtime.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"deepgram-voice-agent\", \"b\": \"inworld-realtime\"}`. From a terminal: `anchor compare deepgram-voice-agent inworld-realtime`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/deepgram-voice-agent.json and https://www.anchorterminal.com/api/v1/tools/inworld-realtime.json\n\n## Other comparisons with Deepgram Voice Agent API or Inworld Realtime API\n\n- [Amazon Nova 2 Sonic vs Deepgram Voice Agent API](https://www.anchorterminal.com/compare/amazon-nova-sonic-vs-deepgram-voice-agent.md)\n- [Amazon Nova 2 Sonic vs Inworld Realtime API](https://www.anchorterminal.com/compare/amazon-nova-sonic-vs-inworld-realtime.md)\n- [AssemblyAI Voice Agent API vs Deepgram Voice Agent API](https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-deepgram-voice-agent.md)\n- [AssemblyAI Voice Agent API vs Inworld Realtime API](https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-inworld-realtime.md)\n- [Bland AI API + MCP vs Deepgram Voice Agent API](https://www.anchorterminal.com/compare/bland-ai-vs-deepgram-voice-agent.md)\n- [Bland AI API + MCP vs Inworld Realtime API](https://www.anchorterminal.com/compare/bland-ai-vs-inworld-realtime.md)\n- [Bolna API + MCP vs Deepgram Voice Agent API](https://www.anchorterminal.com/compare/bolna-vs-deepgram-voice-agent.md)\n- [Bolna API + MCP vs Inworld Realtime API](https://www.anchorterminal.com/compare/bolna-vs-inworld-realtime.md)\n- [Deepgram Voice Agent API vs ElevenLabs Agents API + MCP](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-elevenlabs-agents.md)\n- [Deepgram Voice Agent API vs fone.me](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-fone-me.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 GPT-Live](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-gpt-live.md)\n- [Deepgram Voice Agent API vs Harmony.ai](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-harmony-ai.md)\n- [Deepgram Voice Agent API vs Hume EVI (Empathic Voice Interface)](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-hume-evi.md)\n- [Deepgram Voice Agent API vs LiveKit Agents](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-livekit-agents.md)\n- [Deepgram Voice Agent API vs OpenAI Realtime API](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-openai-realtime.md)\n- [Deepgram Voice Agent API vs Pipecat](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-pipecat.md)\n- [Deepgram Voice Agent API vs PlaceCall](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-placecall.md)\n- [Deepgram Voice Agent API vs Retell AI API + MCP](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-retell-ai.md)\n- [Deepgram Voice Agent API vs Rime Prism](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-rime-prism.md)\n- [Deepgram Voice Agent API vs Synthflow API + MCP](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-synthflow.md)\n- [Deepgram Voice Agent API vs Ultravox Realtime API](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-ultravox.md)\n- [Deepgram Voice Agent API vs Vaani Developer Platform](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-vaani-voice.md)\n- [Deepgram Voice Agent API vs Vapi API + MCP](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-vapi.md)\n- [Deepgram Voice Agent API vs Vocily AI](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-vocily.md)\n- [Deepgram Voice Agent API vs Vogent API](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-vogent.md)\n- [ElevenLabs Agents API + MCP vs Inworld Realtime API](https://www.anchorterminal.com/compare/elevenlabs-agents-vs-inworld-realtime.md)\n- [fone.me vs Inworld Realtime API](https://www.anchorterminal.com/compare/fone-me-vs-inworld-realtime.md)\n- [Gemini Live API vs Inworld Realtime API](https://www.anchorterminal.com/compare/gemini-live-vs-inworld-realtime.md)\n- [GPT-Live vs Inworld Realtime API](https://www.anchorterminal.com/compare/gpt-live-vs-inworld-realtime.md)\n- [Harmony.ai vs Inworld Realtime API](https://www.anchorterminal.com/compare/harmony-ai-vs-inworld-realtime.md)\n- [Hume EVI (Empathic Voice Interface) vs Inworld Realtime API](https://www.anchorterminal.com/compare/hume-evi-vs-inworld-realtime.md)\n- [Inworld Realtime API vs LiveKit Agents](https://www.anchorterminal.com/compare/inworld-realtime-vs-livekit-agents.md)\n- [Inworld Realtime API vs OpenAI Realtime API](https://www.anchorterminal.com/compare/inworld-realtime-vs-openai-realtime.md)\n- [Inworld Realtime API vs Pipecat](https://www.anchorterminal.com/compare/inworld-realtime-vs-pipecat.md)\n- [Inworld Realtime API vs PlaceCall](https://www.anchorterminal.com/compare/inworld-realtime-vs-placecall.md)\n- [Inworld Realtime API vs Retell AI API + MCP](https://www.anchorterminal.com/compare/inworld-realtime-vs-retell-ai.md)\n- [Inworld Realtime API vs Rime Prism](https://www.anchorterminal.com/compare/inworld-realtime-vs-rime-prism.md)\n- [Inworld Realtime API vs Synthflow API + MCP](https://www.anchorterminal.com/compare/inworld-realtime-vs-synthflow.md)\n- [Inworld Realtime API vs Ultravox Realtime API](https://www.anchorterminal.com/compare/inworld-realtime-vs-ultravox.md)\n- [Inworld Realtime API vs Vaani Developer Platform](https://www.anchorterminal.com/compare/inworld-realtime-vs-vaani-voice.md)\n- [Inworld Realtime API vs Vapi API + MCP](https://www.anchorterminal.com/compare/inworld-realtime-vs-vapi.md)\n- [Inworld Realtime API vs Vocily AI](https://www.anchorterminal.com/compare/inworld-realtime-vs-vocily.md)\n- [Inworld Realtime API vs Vogent API](https://www.anchorterminal.com/compare/inworld-realtime-vs-vogent.md)\n- [CueLight vs Deepgram Voice Agent API](https://www.anchorterminal.com/compare/cuelight-vs-deepgram-voice-agent.md)\n- [CueLight vs Inworld Realtime API](https://www.anchorterminal.com/compare/cuelight-vs-inworld-realtime.md)\n- [Deepgram Voice Agent API vs Pipecat PhoneLLM](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-pipecat-phonellm.md)\n- [Inworld Realtime API vs Pipecat PhoneLLM](https://www.anchorterminal.com/compare/inworld-realtime-vs-pipecat-phonellm.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Deepgram Voice Agent API vs Inworld Realtime API", "url": "" } ], "description": "Deepgram Voice Agent scores 72.2 (BB) to Inworld Realtime's 60.1 (C) for voice agents. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Deepgram Voice Agent API BB 72.2", "Inworld Realtime API C 60.1", "scores" ], "h1": "Deepgram Voice Agent API vs Inworld Realtime API", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/deepgram-voice-agent-vs-inworld-realtime", "published": "2026-10-01", "section": "tools", "title": "Deepgram Voice Agent vs Inworld Realtime for AI agents (2026)", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-inworld-realtime" }, "tokens": { "markdown": 5550, "slim": 2830 }, "version": 1 }