# Inworld STT vs OpenAI Speech to Text

> OpenAI Speech to Text scores 75 (BB) to Inworld STT's 54.7 (C) for speech-to-text. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/inworld-stt-vs-openai-speech-to-text
- Markdown: https://www.anchorterminal.com/compare/inworld-stt-vs-openai-speech-to-text.md (~6,000 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

OpenAI Speech to Text scores 75 (BB) on agent readiness against Inworld STT's 54.7 (C), and leads in 6 of 7 scored categories. Inworld STT leads on payments & pricing. Both do speech-to-text.

- Inworld STT: grade C, 54.7/100, rank #895 of 1486. Markdown https://www.anchorterminal.com/tools/inworld-stt.md · JSON https://www.anchorterminal.com/api/v1/tools/inworld-stt.json
- OpenAI Speech to Text: grade BB, 75/100, rank #74 of 1486. Markdown https://www.anchorterminal.com/tools/openai-speech-to-text.md · JSON https://www.anchorterminal.com/api/v1/tools/openai-speech-to-text.json
- Best speech-to-text APIs for AI agents: https://www.anchorterminal.com/best/speech-to-text/index.md
- All 320 stt comparisons: https://www.anchorterminal.com/compare/speech-to-text/index.md

## Which one, for what

### Inworld STT (C)

Good for: Low-cost live transcription for voice agents, with speaker traits.

Ahead on:
- Payments & pricing, 40 against 30

Also in its favour:
- Free to start without a card

Watch for: No OpenAPI or other machine-readable contract

### OpenAI Speech to Text (BB)

Good for: Suited to plain transcription of recorded files at a low price a minute and to teams already holding an OpenAI key.

Ahead on:
- Reliability, 65 against 60
- Schema & documentation, 89 against 54
- Agent ergonomics, 78 against 56
- Security & auth, 97 against 63
- Maintenance & community, 71 against 41
- Transparency & trust, 90 against 60

Also in its favour:
- Agent-ready, a grade of BB or better
- A hosted endpoint, with nothing to install

Watch for: `whisper-1`, `gpt-4o-transcribe`, `gpt-4o-mini-transcribe`, `gpt-4o-transcribe-diarize` and `/v1/audio/translations` shut down on 26 February 2027


## Why the edge

### Schema & documentation: OpenAI Speech to Text +35

- 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.
- OpenAI Speech to Text (89): Model reading. The public OpenAPI 3.1 document in openai/openai-openapi (version 2.3.0, last committed 31 October) covers `/audio/transcriptions` and `/audio/translations` and names `gpt-transcribe` (25). llms.txt and a Markdown twin of every docs page (10). The transcription overview says which model to use for files, live audio, speaker labels, timestamps and translation, and the file guide now opens by recommending `gpt-transcribe` and saying the specialised examples use deprecated models (18 of 20). `response_format`, `timestamp_granularities` and `model` are enums in the document. `language` is a plain string, and which formats each model accepts is stated in prose only (12 of 15). Examples in seven languages and curl, and an error codes page with a cause and fix for each. The Markdown twin of the endpoint reference now lists the body parameters, including `languages` and `keywords` for `gpt-transcribe`, but its first example still names the deprecated `gpt-4o-transcribe`, and the guide lists seven input formats where the document lists nine (12 of 15, was 11). A dated changelog and deprecations page. `gpt-transcribe` has one alias and no dated snapshot to pin (12 of 15). 25 + 10 + 18 + 12 + 12 + 12 = 89.

### Security & auth: OpenAI Speech to Text +34

- Inworld STT (63): Model reading of the checklist, with training and retention in place of the least-privilege and injection lines. 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, via the `bearer_` WebSocket subprotocol, not the URL (25 of 30). The Terms (11 June 2025) say Inworld won't train generally available models on customers' non-public Materials, except feedback and flagged content, while the Privacy Notice (18 January 2026) lists training AI models among its uses, per the inworld-tts check of 4 November (12 of 20). Zero data retention keeps STT audio and transcripts in memory and out of logs, included on Developer ($300 a month) and above per the docs, while the STT page says Enterprise or a Growth add-on. Async results and audio go after 7 days, and no default period is given for logs (8 of 15). Usage is attributed per key and a Performance page shows 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 63.
- OpenAI Speech to Text (97): Model reading, on the lines the OpenAI API and Decisions API listings use. Project keys with permissions per key, service-account keys through the Administration API and workload identity federation, per the Decisions API listing's read of 8 October. The access-control guide, re-read on 1 November, puts audio under one Model capabilities permission with chat completions, embeddings and images, so a restricted key can't be limited to the audio endpoints alone (27 of 30, as the Decisions API listing, was 26). The data controls page says API data isn't used for training unless the customer opts in (20). Both audio endpoints are listed with no abuse-monitoring retention, no application state and Zero Data Retention eligibility, re-read on 1 November (15). The Admin API has an audit log endpoint, and the OpenAPI document has `GET /organization/usage/audio_transcriptions` grouped by project, API key or model, the per-key usage view both other OpenAI listings got 15 for (15, was 13). security.txt, re-read on 1 November, is PGP-signed, names a Bugcrowd programme and a coordinated disclosure policy and has no Expires field. trust.openai.com, read on 1 November, names SOC 2 Type 2 and ISO/IEC 27001, 27017, 27018 and 27701 (20, was 12 when no trust centre was read, the award both other OpenAI listings carry). 27 + 20 + 15 + 15 + 20 = 97.

### Maintenance & community: OpenAI Speech to Text +30

- 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.
- OpenAI Speech to Text (71): Model reading. The last dated change to transcription is still the deprecation notice of 26 August 2026, 67 days before 1 November, after the release of `gpt-transcribe` and `gpt-live-transcribe` on 28 July (20 of 30). The deprecations page promises at least six months' notice for generally available models, and the four transcription models got six months to the day. On 14 October GA GPT-4 series models got 92 days with no reason stated, so the policy reads as a minimum of two to three months in practice, as the OpenAI API and Decisions API listings read it (8 of 12, was 12). Four of the five file transcription models were deprecated within a month of their replacements shipping, and the replacements don't cover diarisation, timestamps or subtitles (2 of 8). The dated changelog has two transcription entries in 90 days among dozens for the API (13 of 15). Python SDK replies were not sampled (5 of 10). Python SDK v3.42.0 was tagged on 31 October 2026, with v3.41.0 on 28 October and v3.40.0 on 27 October (15). CI, CodeQL and a breaking-change check run in the repository (8 of 10). 20 + 8 + 2 + 13 + 5 + 15 + 8 = 71.

### Transparency & trust: OpenAI Speech to Text +30

- 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.
- OpenAI Speech to Text (90): The hosted models are closed with clear terms, the Python SDK Apache-2.0 and the OpenAPI document MIT, per the OpenAI API listing's check of the services agreement. openai.com answered the services agreement with 403 again on 1 November (15, was 12). The data controls page, re-read on 1 November, lists both audio endpoints with no training, no abuse-monitoring retention, no application state and Zero Data Retention eligibility. The DPA, effective 1 January 2026, commits to return or deletion of customer data on termination, 30 days to object to a new subprocessor, and SCCs with the UK Addendum, and nothing in it conflicts with the guide, per the OpenAI API listing's 4 October check, not re-read on 1 November (openai.com answered 403). The same reading as the OpenAI API listing (30 of 30, was 28). A deprecations page with notice periods by model class, dated shutdowns and replacements, including `/v1/audio/translations` to `v1/realtime/translations` (20). Data residency is documented by region and endpoint, with the audio endpoints in every listed region for storage and in the United States and Europe for processing. The subprocessor list, updated 9 July 2026, names third-party subprocessors and OpenAI affiliates with processing countries for each and a form for notice of new ones, per the OpenAI API listing's 4 October check, not re-read on 1 November (openai.com answered 403). The same reading as the OpenAI API listing (20 of 20, was 16). 15 + 30 + 20 + 20 = 85.

### Agent ergonomics: OpenAI Speech to Text +22

- 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.
- OpenAI Speech to Text (78): API reading, as for the other speech-to-text listings. The default `json` response is the text, detected languages and usage, `text` returns a bare string, and segments, words and speaker labels come only when asked for on the models that have them (20 of 25). There is no transcript store to page through. Files stop at 25 MB, the caller splits longer audio, and the `gpt-transcribe` model page marks the Batch API as not supported (10 of 20). Errors carry `message`, `type`, `param` and `code`, and the error codes page gives a fix for each status (18 of 20). The call is stateless and safe to retry, and the Python SDK retries 408, 409, 429 and 5xx twice by default. No idempotency key applies to this endpoint (15 of 20). `file` and `model` are the only required fields, with guide examples for JavaScript, Python, Go, Java, C# and Ruby SDKs and a CLI (15).

### Payments & pricing: Inworld STT +10

- Inworld STT (40): No x402, MPP or L402 (0). Per-hour prices for every plan published without a login (20). On-Demand includes up to 400 minutes of STT and lists no payment method, while async jobs need one (20). A person signs up in the Portal or through `inworld login` in a browser before a key exists (0). Total 40.
- OpenAI Speech to Text (30): No x402, MPP or L402 on the pricing page, re-read on 1 November (0). $0.0045 an audio minute for `gpt-transcribe`, $0.017 for `gpt-live-transcribe` and $0.006 for `whisper-1` on the public pricing page (20). The rate limits guide lists a Free tier capped at $100 a month in allowed countries, while the `gpt-transcribe` model page's rate-limit table starts at Build, which needs $5 of credit. Half, the reading both other OpenAI listings use for the same pages (10, was 0). A person signs up in a browser and creates the key in the console (0). 0 + 20 + 10 + 0 = 30.

## Score by category

| Category | Weight | Inworld STT | OpenAI Speech to Text | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 60 | 65 | OpenAI Speech to Text +5 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 54 | 89 | OpenAI Speech to Text +35 |
| Agent ergonomics | 13% (16.2 this run) | 56 | 78 | OpenAI Speech to Text +22 |
| Security & auth | 14% (17.5 this run) | 63 | 97 | OpenAI Speech to Text +34 |
| Payments & pricing | 10% (12.5 this run) | 40 | 30 | Inworld STT +10 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 41 | 71 | OpenAI Speech to Text +30 |
| Transparency & trust | 7% (8.8 this run) | 60 | 90 | OpenAI Speech to Text +30 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **54.7 · C** | **75 · BB** | |

## Facts side by side

| Fact | Inworld STT | OpenAI Speech to Text |
| --- | --- | --- |
| Kind | Model API | Model API |
| Vendor | Inworld AI | OpenAI |
| Hosted endpoint | no (local only) | `https://api.openai.com/v1` |
| Transports | HTTP, websocket | HTTP, websocket |
| Auth | API key | API key |
| Pricing | Pay per use | Pay per use |
| Price for speech-to-text | $0.0017 per minute of audio | not published |
| x402 | no | no |
| Licence | none | Proprietary hosted service. The service terms were not read (see open questions). The Python SDK is Apache-2.0 and the OpenAPI document is MIT |
| Tools exposed | 0 | none |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-10-29 | 2026-08-26 |
| Terms last updated | 2025-06-11 | couldn't be read |
| Privacy policy last updated | 2026-01-18 | couldn't be read |
| Customer content may train models | not found in the text | couldn't be read |
| Terms restrict automated access | not found in the text | couldn't be read |
| Terms restrict benchmarking | not found in the text | couldn't be read |
| Terms or service can change without notice | not found in the text | couldn't be read |
| Arbitration or class-action waiver | not found in the text | couldn't be read |
| Popularity | none | 32k stars |
| Agent reviews | none | 3.3/5 (4) |

## What the same task costs

| Task | Inworld STT | OpenAI Speech to Text |
| --- | --- | --- |
| Transcribe a one-hour meeting | $0.10 to $0.15 | $0.27 to $1.02 |

## How the scores have moved

### Inworld STT

No score change since it was listed.

### OpenAI Speech to Text

- +2.4 on 1 November 2026: product, new evidence, correction
- +0.2 on 27 October 2026: checklist

## Verdicts

**Inworld STT.** Inworld STT costs $0.10 to $0.15 an hour with 400 free minutes, and covers files, live streams and async jobs in 30 languages with Voice Profile signals. There is no machine-readable spec, no public STT changelog and no readable status history, and diarisation is still experimental.

**OpenAI Speech to Text.** `gpt-transcribe` costs $0.0045 an audio minute, and the audio endpoints keep no abuse-monitoring logs or application state. Speaker labels, word timestamps and subtitles exist only on `whisper-1` and `gpt-4o-transcribe-diarize`, which shut down on 26 February 2027 with no replacement named for those functions.

## Before you call either

### Inworld STT

1. Send the Base64 credential as-is in `Authorization: Basic`; don't encode it again
2. Wrap the first WebSocket message in `transcribeConfig`, because a malformed first frame closes the socket with 1005 and no error
3. Use `POST /stt/v1/transcribe:async` for files over about 16 MB and collect the transcript within 7 days
4. Retry 429 or gRPC code 8 with exponential backoff and jitter, and stay within the plan's streaming concurrency
5. Stop sending audio when nobody speaks, since streams are billed for every second sent

### OpenAI Speech to Text

1. Send `gpt-transcribe` to `POST /v1/audio/transcriptions` for recorded files. Use `languages` (a list), not `language`, and never send both.
2. Keep each upload at 25 MB or less. Split longer audio between sentences and pass the previous chunk's text in `prompt`.
3. For speaker labels send `gpt-4o-transcribe-diarize` with `response_format=diarized_json` and `chunking_strategy=auto` for audio over 30 seconds. Plan for its shutdown on 26 February 2027.
4. Word timestamps, `srt` and `vtt` need `whisper-1`, which cannot stream and shuts down on 26 February 2027. Move English translation to `v1/realtime/translations` before then.
5. On 429 or 503 wait at least `Retry-After` when present, then back off with jitter. Do not retry `credit_balance_exhausted` or spend-limit errors.

## Questions

### Which is better for AI agents, Inworld STT or OpenAI Speech to Text?

OpenAI Speech to Text scores 75 (BB) on agent readiness against Inworld STT's 54.7 (C), and leads in 6 of 7 scored categories. Inworld STT leads on payments & pricing.

### Do Inworld STT and OpenAI Speech to Text need an API key?

Both need an API key.

### Can an agent call Inworld STT and OpenAI Speech to Text without installing anything?

No hosted endpoint is listed for Inworld STT. OpenAI Speech to Text has a hosted endpoint at https://api.openai.com/v1.


## For agents

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

## Other comparisons with Inworld STT or OpenAI Speech to Text

- [Amazon Transcribe vs Inworld STT](https://www.anchorterminal.com/compare/amazon-transcribe-vs-inworld-stt.md)
- [Amazon Transcribe vs OpenAI Speech to Text](https://www.anchorterminal.com/compare/amazon-transcribe-vs-openai-speech-to-text.md)
- [AssemblyAI Speech-to-Text (Universal) vs Inworld STT](https://www.anchorterminal.com/compare/assemblyai-stt-vs-inworld-stt.md)
- [AssemblyAI Speech-to-Text (Universal) vs OpenAI Speech to Text](https://www.anchorterminal.com/compare/assemblyai-stt-vs-openai-speech-to-text.md)
- [Azure AI Speech speech-to-text vs Inworld STT](https://www.anchorterminal.com/compare/azure-speech-to-text-vs-inworld-stt.md)
- [Azure AI Speech speech-to-text vs OpenAI Speech to Text](https://www.anchorterminal.com/compare/azure-speech-to-text-vs-openai-speech-to-text.md)
- [Cartesia Ink vs Inworld STT](https://www.anchorterminal.com/compare/cartesia-ink-stt-vs-inworld-stt.md)
- [Cartesia Ink vs OpenAI Speech to Text](https://www.anchorterminal.com/compare/cartesia-ink-stt-vs-openai-speech-to-text.md)
- [Deepgram Speech-to-Text (Nova-3, Flux) vs Inworld STT](https://www.anchorterminal.com/compare/deepgram-stt-vs-inworld-stt.md)
- [Deepgram Speech-to-Text (Nova-3, Flux) vs OpenAI Speech to Text](https://www.anchorterminal.com/compare/deepgram-stt-vs-openai-speech-to-text.md)
- [ElevenLabs Scribe Speech to Text API vs Inworld STT](https://www.anchorterminal.com/compare/elevenlabs-scribe-vs-inworld-stt.md)
- [ElevenLabs Scribe Speech to Text API vs OpenAI Speech to Text](https://www.anchorterminal.com/compare/elevenlabs-scribe-vs-openai-speech-to-text.md)
- [Giggy Speech to Text vs Inworld STT](https://www.anchorterminal.com/compare/giggy-stt-vs-inworld-stt.md)
- [Giggy Speech to Text vs OpenAI Speech to Text](https://www.anchorterminal.com/compare/giggy-stt-vs-openai-speech-to-text.md)
- [Gladia Speech-to-Text API + MCP vs Inworld STT](https://www.anchorterminal.com/compare/gladia-stt-vs-inworld-stt.md)
- [Gladia Speech-to-Text API + MCP vs OpenAI Speech to Text](https://www.anchorterminal.com/compare/gladia-stt-vs-openai-speech-to-text.md)
- [Google Cloud Speech-to-Text vs Inworld STT](https://www.anchorterminal.com/compare/google-speech-to-text-vs-inworld-stt.md)
- [Google Cloud Speech-to-Text vs OpenAI Speech to Text](https://www.anchorterminal.com/compare/google-speech-to-text-vs-openai-speech-to-text.md)
- [Groq Speech-to-Text vs Inworld STT](https://www.anchorterminal.com/compare/groq-speech-to-text-vs-inworld-stt.md)
- [Groq Speech-to-Text vs OpenAI Speech to Text](https://www.anchorterminal.com/compare/groq-speech-to-text-vs-openai-speech-to-text.md)
- [IBM Watson Speech to Text vs Inworld STT](https://www.anchorterminal.com/compare/ibm-watson-stt-vs-inworld-stt.md)
- [IBM Watson Speech to Text vs OpenAI Speech to Text](https://www.anchorterminal.com/compare/ibm-watson-stt-vs-openai-speech-to-text.md)
- [Inworld STT vs MiniMax Speech-to-Text](https://www.anchorterminal.com/compare/inworld-stt-vs-minimax-stt.md)
- [Inworld STT vs Mistral Voxtral Transcribe](https://www.anchorterminal.com/compare/inworld-stt-vs-mistral-voxtral-transcribe.md)
- [Inworld STT vs Rev AI Speech-to-Text API](https://www.anchorterminal.com/compare/inworld-stt-vs-rev-ai-stt.md)
- [Inworld STT vs Smallest.ai Pulse STT](https://www.anchorterminal.com/compare/inworld-stt-vs-smallest-pulse-stt.md)
- [Inworld STT vs Soniox Speech-to-Text](https://www.anchorterminal.com/compare/inworld-stt-vs-soniox-stt.md)
- [Inworld STT vs Speechmatics Speech-to-Text](https://www.anchorterminal.com/compare/inworld-stt-vs-speechmatics-stt.md)
- [MiniMax Speech-to-Text vs OpenAI Speech to Text](https://www.anchorterminal.com/compare/minimax-stt-vs-openai-speech-to-text.md)
- [Mistral Voxtral Transcribe vs OpenAI Speech to Text](https://www.anchorterminal.com/compare/mistral-voxtral-transcribe-vs-openai-speech-to-text.md)
- [OpenAI Speech to Text vs Rev AI Speech-to-Text API](https://www.anchorterminal.com/compare/openai-speech-to-text-vs-rev-ai-stt.md)
- [OpenAI Speech to Text vs Smallest.ai Pulse STT](https://www.anchorterminal.com/compare/openai-speech-to-text-vs-smallest-pulse-stt.md)
- [OpenAI Speech to Text vs Soniox Speech-to-Text](https://www.anchorterminal.com/compare/openai-speech-to-text-vs-soniox-stt.md)
- [OpenAI Speech to Text vs Speechmatics Speech-to-Text](https://www.anchorterminal.com/compare/openai-speech-to-text-vs-speechmatics-stt.md)

---

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