# CueLight vs Inworld Realtime API (slim)

> Inworld Realtime scores 60.1 (C) to CueLight's 47.8 (D) for voice pipeline. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/cuelight-vs-inworld-realtime.md (~5,000 tokens) · this version ~2,680 tokens · JSON https://www.anchorterminal.com/compare/cuelight-vs-inworld-realtime.json · canonical https://www.anchorterminal.com/compare/cuelight-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 CueLight's 47.8 (D), and leads in 6 of 7 scored categories. CueLight leads on payments & pricing. Both do voice pipeline.

- CueLight: D 47.8, rank #1142 of 1510 · https://www.anchorterminal.com/tools/cuelight.min.md
- Inworld Realtime API: C 60.1, rank #671 of 1510 · https://www.anchorterminal.com/tools/inworld-realtime.min.md
- CueLight, good for A turn-detection component for teams assembling their own voice pipeline (OpenVoiceOS, Pipecat-style stacks), especially on small devices. Ahead on Payments & pricing, 60 against 40. Also No key needed to call it; Free to start without a card; Open source.
- Inworld Realtime API, good for Teams moving off OpenAI's Realtime API who want a choice of LLM and Inworld voices. Ahead on Reliability, 62 against 24; Schema & documentation, 60 against 50; Agent ergonomics, 68 against 61; Security & auth, 58 against 50; Maintenance & community, 71 against 41.

| Category | CueLight | Inworld Realtime API |
| --- | --- | --- |
| Reliability (16%) | 24 | 62 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 50 | 60 |
| Agent ergonomics (13%) | 61 | 68 |
| Security & auth (14%) | 50 | 58 |
| Payments & pricing (10%) | 60 | 40 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 41 | 71 |
| Transparency & trust (7%) | 59 | 63 |

| Fact (where they differ) | CueLight | Inworld Realtime API |
| --- | --- | --- |
| Kind | SDK + MCP | HTTP API |
| Vendor | sshah03 (individual developer, name not stated) | Inworld AI |
| Transports |  | websocket, HTTP |
| Auth | None | API key |
| Pricing | Free | Pay per use |
| Licence | Apache-2.0 | none |
| Tools exposed | none | 0 |
| llms.txt | no | yes |
| Last release | 2026-10-14 | 2026-10-16 |
| Terms last updated | no document linked | 2025-06-11 |
| Privacy policy last updated | no document linked | 2026-01-18 |
| Customer content may train models | not read yet | not found in the text |
| Terms restrict automated access | not read yet | not found in the text |
| Terms restrict benchmarking | not read yet | not found in the text |
| Terms or service can change without notice | not read yet | not found in the text |
| Arbitration or class-action waiver | not read yet | not found in the text |
| Popularity | 10 stars | none |

Why the edge:
- Reliability, Inworld Realtime API +38: CueLight 24 (Read as local software. Installs with pip from the Git repository, not from PyPI, with Python 3.10 or later and its dependencies declared in pyproject.toml, a partial held from 15 October (10 of 20). The repository holds two tests (streaming matches whole-sequence output, chunk size is enforced), but it has no GitHub workflow at all, so no public CI runs them (0). No issues or pull requests were open on 15 October, and GitHub's pages were not re-read on 4 November, so the earlier partial is held (12 of 25). Version 0.1.0 in pyproject.toml with no tags or changelog (2 of 15). Below 1.0, and the README calls it a first iteration (0). 10 + 0 + 12 + 2 + 0 = 24.); 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.)
- Maintenance & community, Inworld Realtime API +30: CueLight 41 (Published on 14 October 2026, 21 days before this check (30). A second commit on 15 October added an 8-bit Nano ONNX model to the browser demo, with no version change, tag or changelog entry, so it isn't a release. One publication in 90 days, below the three the line needs (0). No issues or pull requests were open on 15 October, and GitHub's pages were not re-read, so responsiveness is held (5 of 25). Not on PyPI as of 15 October (pypi.org did not resolve on 4 November). The weights are on Hugging Face and the package installs only from Git (3 of 15). Dependencies are current minimums (torch 2.1 or later), with no lockfile, Dependabot or CI (3 of 10). 30 + 0 + 5 + 3 + 3 = 41.); 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.)
- Payments & pricing, CueLight +20: CueLight 60 (No payment protocol (0). Read with the self-hosted rule. Apache-2.0 code and weights with no hosted or paid option (20). No card or account (20). Weights download anonymously, with no signup (20). 0 + 20 + 20 + 20 = 60.); 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, Inworld Realtime API +10: CueLight 50 (Library reading. No OpenAPI applies. The public classes are small, with type hints on most signatures and frozen dataclasses for both policies, though `push` takes an untyped chunk (15 of 25). No llms.txt on the Pages site, and docs are the README (0). The README says which model suits which device, when to choose each preset, and states the limits (English only, audio only, Base's CPU cost) (16 of 20). The 320-sample frame is enforced by an assert, while an unknown preset name falls back silently to default thresholds rather than raising (8 of 15). Quick-start snippets and two example scripts. Error behaviour is not documented (8 of 15). A version number in pyproject.toml and `__version__`, with no changelog (3 of 15). 15 + 0 + 16 + 8 + 8 + 3 = 50.); 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.)
- Security & auth, Inworld Realtime API +8: CueLight 50 (Local-software reading. No credential and no open port. The code runs in the caller's process, weights load from safetensors rather than pickle, but `snapshot_download` fetches the main branch of each Hugging Face repository with no pinned revision (20 of 30). It only classifies audio and takes no actions (16 of 20). It returns probabilities, not content from third parties (10). No logging. Per-frame probabilities and a reset counter are visible to the caller (4 of 15). No SECURITY.md, disclosure policy, security.txt or advisories (0 of 20). 20 + 16 + 10 + 4 + 0 = 50. Re-read from the source on 4 November, unchanged.); 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.)
- Agent ergonomics, Inworld Realtime API +7: CueLight 61 (Library reading. Four public names and one call per frame, with an 11 KB README, so the context cost of learning it is low (22 of 25). Output is one probability and one speech probability per frame, and thresholds, minimum silence, timeout and reset behaviour can all be set (14 of 20). The only error is an assert on chunk size, which `python -O` strips, and a mistyped preset gives defaults without a warning (6 of 20). `push` is stateful by design. `clear()` resets between calls and the detector resets itself at each new turn, and the source shows streaming matches whole-clip output to 1e-4 (10 of 20). One required argument with working defaults. Python only, with ONNX step files and a browser demo but no packaged second-language SDK (9 of 15). 22 + 14 + 6 + 10 + 9 = 61.); Inworld Realtime API 68 (Scored as an API. Conversation history defaults to the last 100 items, can be trimmed, and can be cached on Anthropic models, and every `response.done` carries a `usage` block (18 of 25). No lists to page. Output controls are modalities, turn detection settings, optional transcription and `response.speak` (12 of 20). Error events follow OpenAI's `type` and `code` shape, unsupported fields come back as non-fatal `unsupported_field` warnings, and `item_not_found` names the bad parameter (14 of 20). Tools run on the client and a follow-up response starts automatically after a tool result. Nothing covers side effects of a tool call cut off by an interruption (12 of 20). Works with OpenAI Realtime clients after changing the URL and key, with no Inworld Realtime SDK (12 of 15). Total 68.)