# Change history: Speech Recognition

[← Changelog](/docs/changelog). Entries: 22.

- 2026-09-30 [FIX-0930-27: speech recognition with a disabled model now answers 404 before recognition](/docs/changelog/2026-09-30#fix-0930-27-speech-recognition-with-a-disabled-model-now-answers-404-before-recognition)
- 2026-09-11 [FIX-0911-5: audio transcription tells an input error apart from a service failure](/docs/changelog/2026-09-11#fix-0911-5-audio-transcription-tells-an-input-error-apart-from-a-service-failure)
- 2026-09-10 [BC-0910-1: a network failure on the way to the provider arrives under its own code ai_provider_network](/docs/changelog/2026-09-10#bc-0910-1-a-network-failure-on-the-way-to-the-provider-arrives-under-its-own-code-ai_provider_network)
- 2026-09-10 [FIX-0910-2: AI provider errors now carry the pause from the provider's own header, in one shape for every stream](/docs/changelog/2026-09-10#fix-0910-2-ai-provider-errors-now-carry-the-pause-from-the-provider-s-own-header-in-one-shape-for-every-stream)
- 2026-09-09 [BC-0909-1: Audio transcription retains subscription billing when Cowork/Code is disabled](/docs/changelog/2026-09-09#bc-0909-1-audio-transcription-retains-subscription-billing-when-cowork-code-is-disabled)
- 2026-09-03 [NEW-0903-20: speech-to-text error texts no longer name the recognition engine](/docs/changelog/2026-09-03#new-0903-20-speech-to-text-error-texts-no-longer-name-the-recognition-engine)
- 2026-09-01 [FIX-0901-9: file uploads and AI requests now answer 429 under memory pressure](/docs/changelog/2026-09-01#fix-0901-9-file-uploads-and-ai-requests-now-answer-429-under-memory-pressure)
- 2026-08-20 [FIX-0820-8: AI provider refusal: a readable message instead of relayed prose, and one error shape for streaming and non-streaming](/docs/changelog/2026-08-20#fix-0820-8-ai-provider-refusal-a-readable-message-instead-of-relayed-prose-and-one-error-shape-for-streaming-and-non-streaming)
- 2026-08-16 [NEW-0816-3: new 402 company_budget_exhausted rejection on calls that spend credits](/docs/changelog/2026-08-16#new-0816-3-new-402-company_budget_exhausted-rejection-on-calls-that-spend-credits)
- 2026-08-14 [BC-0814-10: audio transcription accepts the file only in the file field, never truncates it silently, and returns a recognition refusal as 400](/docs/changelog/2026-08-14#bc-0814-10-audio-transcription-accepts-the-file-only-in-the-file-field-never-truncates-it-silently-and-returns-a-recognition-refusal-as-400)
- 2026-08-14 [NEW-0814-12: audio transcription can now draw on the Cowork/Code subscription quota](/docs/changelog/2026-08-14#new-0814-12-audio-transcription-can-now-draw-on-the-cowork-code-subscription-quota)
- 2026-08-11 [FIX-0811-23: the ai_congested retry pause now scales with the configured base and is capped](/docs/changelog/2026-08-11#fix-0811-23-the-ai_congested-retry-pause-now-scales-with-the-configured-base-and-is-capped)
- 2026-08-06 [FIX-0806-6: speech recognition now reports a temporary provider pause](/docs/changelog/2026-08-06#fix-0806-6-speech-recognition-now-reports-a-temporary-provider-pause)
- 2026-08-06 [FIX-0806-7: speech recognition now really waits the stated 15 minutes](/docs/changelog/2026-08-06#fix-0806-7-speech-recognition-now-really-waits-the-stated-15-minutes)
- 2026-07-25 [NEW-0725-2: model calls with a short-lived token issued to a partner system](/docs/changelog/2026-07-25#new-0725-2-model-calls-with-a-short-lived-token-issued-to-a-partner-system)
- 2026-07-14 [FIX-0714-21: Transcription: wallet check before the recognition call](/docs/changelog/2026-07-14#fix-0714-21-transcription-wallet-check-before-the-recognition-call)
- 2026-07-10 [NEW-0710-16: AI quota pacing: pacing field in the response and 429 ai_pacing_limited error](/docs/changelog/2026-07-10#new-0710-16-ai-quota-pacing-pacing-field-in-the-response-and-429-ai_pacing_limited-error)
- 2026-07-06 [NEW-0706-2: New 402 error code ai_quota_exhausted on AI endpoints](/docs/changelog/2026-07-06#new-0706-2-new-402-error-code-ai_quota_exhausted-on-ai-endpoints)
- 2026-07-06 [FIX-0706-3: Over-quota AI usage is charged at the model's base catalog price](/docs/changelog/2026-07-06#fix-0706-3-over-quota-ai-usage-is-charged-at-the-model-s-base-catalog-price)
- 2026-07-05 [NEW-0705-5: New 402 error code ai_quota_exhausted on AI endpoints](/docs/changelog/2026-07-05#new-0705-5-new-402-error-code-ai_quota_exhausted-on-ai-endpoints)
- 2026-07-03 [NEW-0703-4: Quality and timestamp parameters in audio transcription](/docs/changelog/2026-07-03#new-0703-4-quality-and-timestamp-parameters-in-audio-transcription)
- 2026-06-16 [FIX-0616-2: transcription response format](/docs/changelog/2026-06-16#fix-0616-2-transcription-response-format)