Inworld STT vs OpenAI Speech to Text

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.

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.

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.

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.

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).

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.