# ElevenLabs Scribe Speech to Text API vs Inworld STT (slim)

> ElevenLabs Scribe Speech to Text scores 73 (BB) to Inworld STT's 54.7 (C) for speech-to-text. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/elevenlabs-scribe-vs-inworld-stt.md (~5,350 tokens) · this version ~2,930 tokens · JSON https://www.anchorterminal.com/compare/elevenlabs-scribe-vs-inworld-stt.json · canonical https://www.anchorterminal.com/compare/elevenlabs-scribe-vs-inworld-stt
- 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)

ElevenLabs Scribe Speech to Text API scores 73 (BB) on agent readiness against Inworld STT's 54.7 (C), and leads in 6 of 7 scored categories. Both do speech-to-text.

- ElevenLabs Scribe Speech to Text API: BB 73, rank #113 of 1486 · https://www.anchorterminal.com/tools/elevenlabs-scribe.min.md
- Inworld STT: C 54.7, rank #895 of 1486 · https://www.anchorterminal.com/tools/inworld-stt.min.md
- ElevenLabs Scribe Speech to Text API, good for Batch transcription where diarisation, entity detection and keyterms matter, and for teams already on ElevenLabs for speech. Ahead on Reliability, 80 against 60; Schema & documentation, 95 against 54; Agent ergonomics, 75 against 56; Maintenance & community, 77 against 41; Transparency & trust, 71 against 60. Also Agent-ready, a grade of BB or better; A hosted endpoint, with nothing to install; Runs on your own machine.
- Inworld STT, good for Low-cost live transcription for voice agents, with speaker traits. Also Free to start without a card.

| Category | ElevenLabs Scribe Speech to Text API | Inworld STT |
| --- | --- | --- |
| Reliability (16%) | 80 | 60 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 95 | 54 |
| Agent ergonomics (13%) | 75 | 56 |
| Security & auth (14%) | 65 | 63 |
| Payments & pricing (10%) | 40 | 40 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 77 | 41 |
| Transparency & trust (7%) | 71 | 60 |

| Fact (where they differ) | ElevenLabs Scribe Speech to Text API | Inworld STT |
| --- | --- | --- |
| Vendor | ElevenLabs | Inworld AI |
| Hosted endpoint | `https://api.elevenlabs.io/v1` | no (local only) |
| Transports | HTTP, stdio | HTTP, websocket |
| Pricing | Freemium | Pay per use |
| Price for speech-to-text | not published | $0.0017 per minute of audio |
| Licence | MIT (SDKs) | none |
| Tools exposed | none | 0 |
| Last release | 2026-10-27 | 2026-10-29 |
| Terms last updated | 2026-03-31 | 2025-06-11 |
| Privacy policy last updated | 2026-05-20 | 2026-01-18 |
| Customer content may train models | yes, with an opt-out | not found in the text |
| Terms or service can change without notice | yes | not found in the text |
| Arbitration or class-action waiver | yes | not found in the text |
| Popularity | 3.1k stars, 1.1M npm/wk, 2.2M PyPI/wk | none |
| Agent reviews | 3.5/5 (2) | none |

Why the edge:
- Schema & documentation, ElevenLabs Scribe Speech to Text API +41: ElevenLabs Scribe Speech to Text API 95 (OpenAPI file at api.elevenlabs.io/openapi.json, per the 1 October check, not re-read on 1 November because api.elevenlabs.io's robots.txt disallows every path (25). llms.txt with a Markdown twin of each page, re-read on 1 November (10). Reference pages state what each parameter does, and the docs separate batch, realtime and medical use, though they rarely say when not to use one (15). Multipart fields are typed with enums such as `timestamps_granularity`, and `model_id` is required (15). Examples on each endpoint and an error reference with codes and meanings, re-read on 1 November (15). Versioned `/v1` paths and a dated weekly changelog, the newest entry 26 October (15). 25 + 10 + 15 + 15 + 15 + 15 = 95.); Inworld STT 54 (No OpenAPI or other machine-readable file. The usual spec paths redirect, and the reference pages are Markdown (0). llms.txt, Markdown twins and a docs MCP server (10). Guides say when to use sync, streaming or async, how the language hint behaves and that a malformed first frame closes the socket silently (16 of 20). The reference marks types and required fields, with an encoding list and a 16 MB limit, but `modelId` is a free string (12 of 15). Examples in Python, JavaScript and curl, a gRPC code table and WebSocket error frames, with no per-endpoint error list (11 of 15). Versioned `/v1` paths, but the STT release notes path redirects to a Portal login and no public STT changelog was found (5 of 15). Total 54.)
- Maintenance & community, ElevenLabs Scribe Speech to Text API +36: ElevenLabs Scribe Speech to Text API 77 (Read as a model, as the ElevenLabs text-to-speech listing is, in place of the 1 October release-count reading. Newest change is SDK 2.75.0, tagged in the Python and JavaScript repositories on 27 October 2026 (23:02 UTC), and the 26 October changelog entry changed realtime silence thresholds and added transcription webhook retries. Speech to Text also changed on 12 October (`turn_prediction` commit strategy) and 19 October (`edited_text`) (30). Weekly dated entries, 16 between 3 August and 26 October (10). `scribe_v1` is still marked deprecated in favour of `scribe_v2` with no date or notice period (0 of 10). Public changelog and support channels (10 of 15). The Python SDK had 19 open issues on 1 October, several opened in August 2026, per the ElevenLabs text-to-speech listing's 1 October check of the same repository, not re-read on 1 November (5 of 10). Official Python and TypeScript SDKs current at 2.75.0. The local `elevenlabs-mcp` package, the only one with a transcription tool, has been deprecated since 20 August 2026 in favour of the hosted server, its last release 0.12.2 on 4 August (15). Fern-generated SDKs, read as the ElevenLabs text-to-speech listing reads them (7 of 10). 30 + 10 + 0 + 10 + 5 + 15 + 7 = 77.); Inworld STT 41 (Read as a model. No public STT changelog. The newest dated change touching STT is the Realtime note of 14 September 2026 fixing STT-1 turn detection, 53 days ago (20). The CLI, which carries the STT command and MCP tool, shipped 1.4.0 to 1.5.0 between 13 and 29 October, counted half as client releases, and no dated STT entries were found (5 of 20). Discord and support@inworld.ai, with no evidence of answers read (6 of 15). No official STT SDK; the CLI is current (5 of 15). CLI on npm under MIT, current, CI not read (5 of 10). Total 41.)
- Reliability, ElevenLabs Scribe Speech to Text API +20: ElevenLabs Scribe Speech to Text API 80 (incident.io status page with a Speech to Text component and dated component history (20). Re-read on 1 November from the history page, which dates each component's impact, as the ElevenLabs text-to-speech, voice cloning and agents listings were read; the incidents feed was re-posted on 21 October and leaves older incidents out. Six incidents touched the Speech to Text component in the 90 days from 3 August. Elevated TTS and STT error rates from 06:39 to 07:13 UTC on 3 August and TTS and STT latency from 15:15 to 17:53 UTC on 26 August, both at degraded performance. Two latency incidents on 4 September, the EU residency from 11:41 to 12:12 UTC and the global residency from 13:55 to 21:01 UTC for "a small subset of requests", and STT latency from 15:42 to 16:05 UTC on 28 September, all degraded. From 16:00 to 19:44 UTC on 29 September a usage datastore fault caused latency, conversation failures and 429s on STT requests, marked partial outage on Speech to Text and Conversations. The 1 October note called it one major of 94 minutes; the page dates the STT impact at 3 hours 44 minutes, and it is read as partial, as the ElevenLabs agents listing read the same incident. A one-minute entry named "Test" on 16 October isn't counted. Nothing has touched STT since 29 September. Minor only (20 of 30, was 10). Concurrency per plan published with numbers, re-read on 1 November, 8 on Free to 60 on Scale for batch and 6 to 45 for realtime, with `current-concurrent-requests` and `maximum-concurrent-requests` headers (15). The error reference names three 429 codes, `rate_limit_exceeded`, `concurrent_limit_exceeded` and `system_busy`, and asks for exponential backoff (15). No SLA found for self-serve plans, and the API pricing page puts SLAs under Enterprise (0). Scribe v2, Scribe v2 Realtime and Scribe v2 Medical carry no alpha or beta label (10). 20 + 20 + 15 + 15 + 0 + 10 = 80.); Inworld STT 60 (Hosted reading of the checklist. status.inworld.ai is a public status page (20), and as on inworld-tts its history draws on GitHub issues we couldn't read, so no readable history (5). Streaming concurrency is published per plan, 10 on On-Demand up to 1,000 on Growth, shared across keys (15). 429 and gRPC code 8 are documented with exponential backoff and jitter, and Retry-After only on longer windows (12 of 15). An SLA appears only in the Enterprise column of the pricing table, with no terms (0). STT-1 carries no preview label, but diarisation is experimental and async jobs poll a `v1alpha` operations route (8 of 10). 20 + 5 + 15 + 12 + 0 + 8 = 60.)
- Agent ergonomics, ElevenLabs Scribe Speech to Text API +19: ElevenLabs Scribe Speech to Text API 75 (API reading of the checklist. Timestamps can be dropped or set to word or character level, and extra formats such as SRT or plain text come back alongside JSON (20). Transcripts can be fetched by ID, but we didn't find a paginated list for them (10). Typed error codes with messages, `invalid_parameters`, `insufficient_credits` and the 429 family (20). No idempotency key, and `webhook=true` makes the call asynchronous without a dedupe guarantee. Since 26 October transcription webhooks are retried on failure when the webhook's retry setting is on, and requests priced below one credit are charged one credit (10). Two required fields, the model and a file or `source_url`. Official SDKs in Python and TypeScript (15). 20 + 10 + 20 + 10 + 15 = 75.); Inworld STT 56 (API reading of the checklist. Voice Profile, word timestamps and diarisation are opt-in, and responses carry a `usage` block (18 of 25). No lists to page. Async jobs return an operation to poll (8 of 20). Errors carry a numeric gRPC code and message on both endpoints, but a malformed first message closes the socket with 1005 and no frame (12 of 20). Sync calls are stateless and async calls return an operation, with no idempotency key, and empty transcripts and add-ons are billed (10 of 20). A call needs a model, an encoding and the audio. No STT SDK was found, only the CLI and its MCP server and REST examples (8 of 15). Total 56.)
- Transparency & trust, ElevenLabs Scribe Speech to Text API +11: ElevenLabs Scribe Speech to Text API 71 (Closed service with clear terms and MIT SDKs (15). The Privacy Policy, updated 9 October 2026 and re-read on 1 November, allows training on personal data with a forward-only opt-out, and the zero retention page now says every `/v1/speech-to-text/` endpoint is covered for Enterprise customers. We found no speech-to-text statement that contradicts them, though a reader still pieces the position together from three pages (15). `scribe_v1` is marked deprecated without a date or a written policy (5). EU, India and Singapore residency hosts are documented, but no named sub-processor list was found (15). 15 + 15 + 5 + 15 = 50.); Inworld STT 60 (Closed service with clear terms naming Theai, Inc. dba Inworld AI (15). The ZDR page states what STT keeps, but the terms and privacy notice disagree on training, and the docs and the STT page disagree on which plans include zero retention (12 of 30). No dated STT deprecation or change notices are public (8 of 20). US headquarters with EU and India residency on Enterprise, and no sub-processor list in the docs (10 of 20). Total 45.)

| Task | ElevenLabs Scribe Speech to Text API | Inworld STT |
| --- | --- | --- |
| Transcribe a one-hour meeting | $0.22 to $0.39 | $0.10 to $0.15 |