# AssemblyAI Voice Agent API vs Inworld Realtime API

> 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.

- Canonical: https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-inworld-realtime
- Markdown: https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-inworld-realtime.md (~5,000 tokens)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-07

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: grade C, 56.4/100, rank #822 of 1486. Markdown https://www.anchorterminal.com/tools/assemblyai-voice-agent.md · JSON https://www.anchorterminal.com/api/v1/tools/assemblyai-voice-agent.json
- Inworld Realtime API: grade C, 60.1/100, rank #668 of 1486. Markdown https://www.anchorterminal.com/tools/inworld-realtime.md · JSON https://www.anchorterminal.com/api/v1/tools/inworld-realtime.json
- Best conversational voice-agent APIs: https://www.anchorterminal.com/best/voice-agents/index.md
- All 518 voice agents comparisons: https://www.anchorterminal.com/compare/voice-agents/index.md

## Which one, for what

### AssemblyAI Voice Agent API (C)

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 in its favour:
- A hosted endpoint, with nothing to install

Watch for: No Voice Agent API price on the pricing page or in the billing docs on 2 November 2026, and the free credit no longer names it

### Inworld Realtime API (C)

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 in its favour:
- No incidents deducted, where AssemblyAI Voice Agent API loses 3 points for them

Watch for: No per-minute price. A session's cost depends on STT, LLM tokens and TTS characters, and interrupted segments are still billed


## 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.

## Score by category

| Category | Weight | AssemblyAI Voice Agent API | Inworld Realtime API | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 65 | 62 | AssemblyAI Voice Agent API +3 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 83 | 60 | AssemblyAI Voice Agent API +23 |
| Agent ergonomics | 13% (16.2 this run) | 72 | 68 | AssemblyAI Voice Agent API +4 |
| Security & auth | 14% (17.5 this run) | 55 | 58 | Inworld Realtime API +3 |
| Payments & pricing | 10% (12.5 this run) | 0 | 40 | Inworld Realtime API +40 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 64 | 71 | Inworld Realtime API +7 |
| Transparency & trust | 7% (8.8 this run) | 68 | 63 | AssemblyAI Voice Agent API +5 |
| Negative events | ≤15 | -3 | 0 | |
| **Total** | | **56.4 · C** | **60.1 · C** | |

## Facts side by side

| Fact | AssemblyAI Voice Agent API | Inworld Realtime API |
| --- | --- | --- |
| Kind | HTTP API | HTTP API |
| Vendor | AssemblyAI, Inc. | Inworld AI |
| Hosted endpoint | `wss://agents.assemblyai.com/v1/ws` | no (local only) |
| Transports | HTTP | websocket, HTTP |
| Auth | API key | API key |
| Pricing | Pay per use | Pay per use |
| Price for voice agents | not published | $25 per 1M characters |
| x402 | no | no |
| Licence | Proprietary service under AssemblyAI's Terms of Service. The two starter repositories on GitHub carry no licence file | none |
| Tools exposed | none | 0 |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| 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 |
| Terms or service can change without notice | not found in the text | not found in the text |
| Arbitration or class-action waiver | not found in the text | not found in the text |
| Agent reviews | 3.5/5 (4) | none |

## How the scores have moved

### AssemblyAI Voice Agent API

- -8.2 on 2 November 2026 (B to C): pricing, correction
- +0.2 on 27 October 2026: checklist

### Inworld Realtime API

No score change since it was listed.

## Verdicts

**AssemblyAI Voice Agent API.** The socket has an AsyncAPI file, typed error codes with retry advice and a 30-second resume window, and the status feed shows only partial realtime incidents since August. On 2 November AssemblyAI's pricing page and billing docs no longer listed the API or its rate, no concurrent-session limit is published, and telephony is inbound only.

**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.

## Before you call either

### AssemblyAI Voice Agent API

1. Send `session.end` before closing the socket. Without it the session stays resumable, and billed, for 30 seconds
2. Retry only `at_capacity`, `concurrency_exceeded` and `internal_error`, with backoff. Every other session error code is fatal
3. Send `tool.result` inside the `reply.done` handler, not straight after `tool.call`
4. Mint a one-time token with `GET /v1/token` for browser clients and never ship the API key to a page
5. Deduplicate webhooks on `event_id`, and verify `X-AAI-Signature` against the raw body bytes because a 401 is not retried

### Inworld Realtime API

1. Set the auto follow-up off if your client sends its own `response.create` after a tool result, or replies double
2. Read `response.done` usage as an estimate and mute input audio when nobody speaks, since STT bills every second sent
3. Use `response.speak` for fixed greetings, which skips the LLM
4. Treat `unsupported_field` errors as warnings and keep the session open
5. Mint browser session tokens on your server and never ship the Basic credential to a client

## Questions

### Which is better for AI agents, AssemblyAI Voice Agent API or Inworld Realtime API?

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.

### Do AssemblyAI Voice Agent API and Inworld Realtime API need an API key?

Both need an API key.

### Can an agent call AssemblyAI Voice Agent API and Inworld Realtime API without installing anything?

AssemblyAI Voice Agent API has a hosted endpoint at wss://agents.assemblyai.com/v1/ws. No hosted endpoint is listed for Inworld Realtime API.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-inworld-realtime.json, and with the fewest tokens: https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-inworld-realtime.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "assemblyai-voice-agent", "b": "inworld-realtime"}`. From a terminal: `anchor compare assemblyai-voice-agent inworld-realtime`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/assemblyai-voice-agent.json and https://www.anchorterminal.com/api/v1/tools/inworld-realtime.json

## Other comparisons with AssemblyAI Voice Agent API or Inworld Realtime API

- [Amazon Nova 2 Sonic vs AssemblyAI Voice Agent API](https://www.anchorterminal.com/compare/amazon-nova-sonic-vs-assemblyai-voice-agent.md)
- [Amazon Nova 2 Sonic vs Inworld Realtime API](https://www.anchorterminal.com/compare/amazon-nova-sonic-vs-inworld-realtime.md)
- [AssemblyAI Voice Agent API vs Bland AI API + MCP](https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-bland-ai.md)
- [AssemblyAI Voice Agent API vs Bolna API + MCP](https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-bolna.md)
- [AssemblyAI Voice Agent API vs Deepgram Voice Agent API](https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-deepgram-voice-agent.md)
- [AssemblyAI Voice Agent API vs ElevenLabs Agents API + MCP](https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-elevenlabs-agents.md)
- [AssemblyAI Voice Agent API vs fone.me](https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-fone-me.md)
- [AssemblyAI Voice Agent API vs Gemini Live API](https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-gemini-live.md)
- [AssemblyAI Voice Agent API vs GPT-Live](https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-gpt-live.md)
- [AssemblyAI Voice Agent API vs Harmony.ai](https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-harmony-ai.md)
- [AssemblyAI Voice Agent API vs Hume EVI (Empathic Voice Interface)](https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-hume-evi.md)
- [AssemblyAI Voice Agent API vs LiveKit Agents](https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-livekit-agents.md)
- [AssemblyAI Voice Agent API vs OpenAI Realtime API](https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-openai-realtime.md)
- [AssemblyAI Voice Agent API vs Pipecat](https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-pipecat.md)
- [AssemblyAI Voice Agent API vs PlaceCall](https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-placecall.md)
- [AssemblyAI Voice Agent API vs Retell AI API + MCP](https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-retell-ai.md)
- [AssemblyAI Voice Agent API vs Rime Prism](https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-rime-prism.md)
- [AssemblyAI Voice Agent API vs Synthflow API + MCP](https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-synthflow.md)
- [AssemblyAI Voice Agent API vs Ultravox Realtime API](https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-ultravox.md)
- [AssemblyAI Voice Agent API vs Vaani Developer Platform](https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-vaani-voice.md)
- [AssemblyAI Voice Agent API vs Vapi API + MCP](https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-vapi.md)
- [AssemblyAI Voice Agent API vs Vocily AI](https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-vocily.md)
- [AssemblyAI Voice Agent API vs Vogent API](https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-vogent.md)
- [Bland AI API + MCP vs Inworld Realtime API](https://www.anchorterminal.com/compare/bland-ai-vs-inworld-realtime.md)
- [Bolna API + MCP vs Inworld Realtime API](https://www.anchorterminal.com/compare/bolna-vs-inworld-realtime.md)
- [Deepgram Voice Agent API vs Inworld Realtime API](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-inworld-realtime.md)
- [ElevenLabs Agents API + MCP vs Inworld Realtime API](https://www.anchorterminal.com/compare/elevenlabs-agents-vs-inworld-realtime.md)
- [fone.me vs Inworld Realtime API](https://www.anchorterminal.com/compare/fone-me-vs-inworld-realtime.md)
- [Gemini Live API vs Inworld Realtime API](https://www.anchorterminal.com/compare/gemini-live-vs-inworld-realtime.md)
- [GPT-Live vs Inworld Realtime API](https://www.anchorterminal.com/compare/gpt-live-vs-inworld-realtime.md)
- [Harmony.ai vs Inworld Realtime API](https://www.anchorterminal.com/compare/harmony-ai-vs-inworld-realtime.md)
- [Hume EVI (Empathic Voice Interface) vs Inworld Realtime API](https://www.anchorterminal.com/compare/hume-evi-vs-inworld-realtime.md)
- [Inworld Realtime API vs LiveKit Agents](https://www.anchorterminal.com/compare/inworld-realtime-vs-livekit-agents.md)
- [Inworld Realtime API vs OpenAI Realtime API](https://www.anchorterminal.com/compare/inworld-realtime-vs-openai-realtime.md)
- [Inworld Realtime API vs Pipecat](https://www.anchorterminal.com/compare/inworld-realtime-vs-pipecat.md)
- [Inworld Realtime API vs PlaceCall](https://www.anchorterminal.com/compare/inworld-realtime-vs-placecall.md)
- [Inworld Realtime API vs Retell AI API + MCP](https://www.anchorterminal.com/compare/inworld-realtime-vs-retell-ai.md)
- [Inworld Realtime API vs Rime Prism](https://www.anchorterminal.com/compare/inworld-realtime-vs-rime-prism.md)
- [Inworld Realtime API vs Synthflow API + MCP](https://www.anchorterminal.com/compare/inworld-realtime-vs-synthflow.md)
- [Inworld Realtime API vs Ultravox Realtime API](https://www.anchorterminal.com/compare/inworld-realtime-vs-ultravox.md)
- [Inworld Realtime API vs Vaani Developer Platform](https://www.anchorterminal.com/compare/inworld-realtime-vs-vaani-voice.md)
- [Inworld Realtime API vs Vapi API + MCP](https://www.anchorterminal.com/compare/inworld-realtime-vs-vapi.md)
- [Inworld Realtime API vs Vocily AI](https://www.anchorterminal.com/compare/inworld-realtime-vs-vocily.md)
- [Inworld Realtime API vs Vogent API](https://www.anchorterminal.com/compare/inworld-realtime-vs-vogent.md)
- [AssemblyAI Voice Agent API vs CueLight](https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-cuelight.md)
- [AssemblyAI Voice Agent API vs Pipecat PhoneLLM](https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-pipecat-phonellm.md)
- [CueLight vs Inworld Realtime API](https://www.anchorterminal.com/compare/cuelight-vs-inworld-realtime.md)
- [Inworld Realtime API vs Pipecat PhoneLLM](https://www.anchorterminal.com/compare/inworld-realtime-vs-pipecat-phonellm.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp