# AssemblyAI Voice Agent API vs Inworld Realtime API (slim)

> Inworld Realtime scores 60.1 (C) to AssemblyAI Voice Agent's 56.4 (C) for voice agents. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-inworld-realtime.md (~5,000 tokens) · this version ~2,130 tokens · JSON https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-inworld-realtime.json · canonical https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-inworld-realtime
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-07
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Inworld Realtime API scores 60.1 (C) on agent readiness against AssemblyAI Voice Agent API's 56.4 (C), and leads in 3 of 7 scored categories. AssemblyAI Voice Agent API leads on schema & documentation and transparency & trust. Both do voice agents.

- AssemblyAI Voice Agent API: C 56.4, rank #822 of 1486 · https://www.anchorterminal.com/tools/assemblyai-voice-agent.min.md
- Inworld Realtime API: C 60.1, rank #668 of 1486 · https://www.anchorterminal.com/tools/inworld-realtime.min.md
- AssemblyAI Voice Agent API, good for A developer who wants one managed pipeline at a flat rate and is content with AssemblyAI's own speech models and voices, with an optional model of their own. Ahead on Schema & documentation, 83 against 60; Transparency & trust, 68 against 63. Also A hosted endpoint, with nothing to install.
- Inworld Realtime API, good for Teams moving off OpenAI's Realtime API who want a choice of LLM and Inworld voices. Ahead on Payments & pricing, 40 against 0; Maintenance & community, 71 against 64. Also No incidents deducted, where AssemblyAI Voice Agent API loses 3 points for them.

| Category | AssemblyAI Voice Agent API | Inworld Realtime API |
| --- | --- | --- |
| Reliability (16%) | 65 | 62 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 83 | 60 |
| Agent ergonomics (13%) | 72 | 68 |
| Security & auth (14%) | 55 | 58 |
| Payments & pricing (10%) | 0 | 40 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 64 | 71 |
| Transparency & trust (7%) | 68 | 63 |

| Fact (where they differ) | AssemblyAI Voice Agent API | Inworld Realtime API |
| --- | --- | --- |
| Vendor | AssemblyAI, Inc. | Inworld AI |
| Hosted endpoint | `wss://agents.assemblyai.com/v1/ws` | no (local only) |
| Transports | HTTP | websocket, HTTP |
| Price for voice agents | not published | $25 per 1M characters |
| Licence | Proprietary service under AssemblyAI's Terms of Service. The two starter repositories on GitHub carry no licence file | none |
| Tools exposed | none | 0 |
| Last release | 2026-09-16 | 2026-10-16 |
| Terms last updated | 2026-07-01 | 2025-06-11 |
| Privacy policy last updated | 2026-05-26 | 2026-01-18 |
| Customer content may train models | yes, with an opt-out | not found in the text |
| Terms restrict automated access | yes | not found in the text |
| Terms restrict benchmarking | yes | not found in the text |
| Agent reviews | 3.5/5 (4) | none |

Why the edge:
- Payments & pricing, Inworld Realtime API +40: AssemblyAI Voice Agent API 0 (No x402, MPP or L402 (0 of 40). On 2 November the pricing page lists speech-to-text, dictation, text-to-speech and LLM Gateway prices but no Voice Agent API price, and the billing docs have no Voice Agent section. The $4.50 an hour rate the 9 October check read on both is no longer published, and no other price page was found (0, was 20). The billing docs now say new accounts' $50 of credit applies to pre-recorded and real-time speech-to-text, Speech Understanding and Guardrails, without naming the Voice Agent API, where on 9 October they said it was covered (0, was 20). A person has to sign up in a browser to get the first key, and no key-creation API was found (0). 0+0+0+0 = 0.); Inworld Realtime API 40 (No x402, MPP or L402 (0). No per-session price, but each billed part (STT per hour, TTS per character, LLM per token) is priced publicly (20). On-Demand includes free STT and TTS allowances and lists no payment method, though some premium LLMs need a card on file (20). A person signs up in a browser before a key exists (0). Total 40.)
- Schema & documentation, AssemblyAI Voice Agent API +23: AssemblyAI Voice Agent API 83 (An AsyncAPI 3.0 file describes the socket and an OpenAPI 3.0.3 file the token endpoint. No description file was found for the agents, sessions and webhook REST endpoints, and the AsyncAPI file lacks `language_codes`, `voice_focus`, `transcript.agent.delta` and `is_error`, which the docs added on 23 July 2026 (19 of 25). llms.txt, a Markdown copy of each page and a docs MCP server (10). Operations and fields say what they are for and when to use them, such as when to choose `hold` over `interactive` execution (17 of 20). Enums, ranges and defaults on audio encoding, turn detection and timeouts. Tool `parameters` are a JSON Schema the server does not validate at `session.update` (12 of 15). Examples in cURL, Python and JavaScript, and tables of session error codes with close codes (13 of 15). A dated public changelog tagged by product and a `/v1` path, with no written versioning policy found (12 of 15).); 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.)
- Maintenance & community, Inworld Realtime API +7: AssemblyAI Voice Agent API 64 (The last changelog entry tagged Voice Agent API is Pre-Connect Requests on 16 September 2026 (47 days before 2 November), which the 9 October check didn't count (20). Five tagged entries since 4 August (18 August, three on 26 August, 16 September) (20). A public changelog that records fixes, a support address and a Discord link we did not test (11 of 15 for a closed service). The Python and Node SDKs still have no Voice Agent client (Node 4.42.0 of 26 October added text-to-speech clients), and the two starter repositories were last changed on 16 August 2026 (8 of 15). The starters need no dependencies and have no licence file, tests or CI (5 of 10). 20+20+11+8+5 = 64.); 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.)
- Transparency & trust, AssemblyAI Voice Agent API +5: AssemblyAI Voice Agent API 68 (A closed service with a clear service agreement. The starter repositories have no licence file (15 of 30). The Terms of Service grant a licence to train on Customer Data by default, the opt-out needs a paid plan, and the retention page gives periods for streaming, sync, dictation, asynchronous and LLM Gateway data but none for Voice Agent sessions, which are recorded and stored. A DPA is published and the privacy policy states Data Privacy Framework certification (14 of 30). The changelog dates deprecations ahead of time, such as the 11 July 2026 notice of a change on 7 August, and the terms promise reasonable prior notice of major changes. No written deprecation policy was found (12 of 20). The subprocessor list at /legal/subprocessors redirects to a Vanta trust centre whose robots.txt disallows every path, so it is unread. US and EU endpoints are mentioned, with no EU host named for the Voice Agent API in the pages read (10 of 20). 15+14+12+10 = 51.); 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.)