[{"data":1,"prerenderedAt":7},["ShallowReactive",2],{"docs-changelog\u002Fai-audio":3,"docs-tabs-changelog\u002Fai-audio":6},{"content":4,"lastmod":5},"# Change history: Speech Recognition\n\n[← Changelog](\u002Fdocs\u002Fchangelog). Entries: 27.\n\n- 2026-11-07 [FIX-1107-1: Lifecycle headers for transcription models](\u002Fdocs\u002Fchangelog\u002F2026-11-07#fix-1107-1-lifecycle-headers-for-transcription-models)\n- 2026-10-27 [NEW-1027-5: Exhausted AI quota period in the response](\u002Fdocs\u002Fchangelog\u002F2026-10-27#new-1027-5-exhausted-ai-quota-period-in-the-response)\n- 2026-10-26 [NEW-1026-15: Rejection before a personal model call starts](\u002Fdocs\u002Fchangelog\u002F2026-10-26#new-1026-15-rejection-before-a-personal-model-call-starts)\n- 2026-10-21 [FIX-1021-4: an oversized request to a model: images for bitrix are downscaled, a size refusal is 413 instead of 502](\u002Fdocs\u002Fchangelog\u002F2026-10-21#fix-1021-4-an-oversized-request-to-a-model-images-for-bitrix-are-downscaled-a-size-refusal-is-413-instead-of-502)\n- 2026-10-09 [NEW-1009-5: Cowork quota wall offers a limit reset with a promotion right](\u002Fdocs\u002Fchangelog\u002F2026-10-09#new-1009-5-cowork-quota-wall-offers-a-limit-reset-with-a-promotion-right)\n- 2026-10-09 [NEW-1009-18: Learn-more link in the AI quota 402 refusal](\u002Fdocs\u002Fchangelog\u002F2026-10-09#new-1009-18-learn-more-link-in-the-ai-quota-402-refusal)\n- 2026-09-30 [FIX-0930-27: speech recognition with a disabled model now answers 404 before recognition](\u002Fdocs\u002Fchangelog\u002F2026-09-30#fix-0930-27-speech-recognition-with-a-disabled-model-now-answers-404-before-recognition)\n- 2026-09-11 [FIX-0911-5: audio transcription tells an input error apart from a service failure](\u002Fdocs\u002Fchangelog\u002F2026-09-11#fix-0911-5-audio-transcription-tells-an-input-error-apart-from-a-service-failure)\n- 2026-09-10 [BC-0910-1: a network failure on the way to the provider arrives under its own code ai_provider_network](\u002Fdocs\u002Fchangelog\u002F2026-09-10#bc-0910-1-a-network-failure-on-the-way-to-the-provider-arrives-under-its-own-code-ai_provider_network)\n- 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](\u002Fdocs\u002Fchangelog\u002F2026-09-10#fix-0910-2-ai-provider-errors-now-carry-the-pause-from-the-provider-s-own-header-in-one-shape-for-every-stream)\n- 2026-09-09 [BC-0909-1: Audio transcription retains subscription billing when Cowork is disabled](\u002Fdocs\u002Fchangelog\u002F2026-09-09#bc-0909-1-audio-transcription-retains-subscription-billing-when-cowork-is-disabled)\n- 2026-09-03 [NEW-0903-20: speech-to-text error texts no longer name the recognition engine](\u002Fdocs\u002Fchangelog\u002F2026-09-03#new-0903-20-speech-to-text-error-texts-no-longer-name-the-recognition-engine)\n- 2026-09-01 [FIX-0901-9: file uploads and AI requests now answer 429 under memory pressure](\u002Fdocs\u002Fchangelog\u002F2026-09-01#fix-0901-9-file-uploads-and-ai-requests-now-answer-429-under-memory-pressure)\n- 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](\u002Fdocs\u002Fchangelog\u002F2026-08-20#fix-0820-8-ai-provider-refusal-a-readable-message-instead-of-relayed-prose-and-one-error-shape-for-streaming-and-non-streaming)\n- 2026-08-16 [NEW-0816-3: new 402 company_budget_exhausted rejection on calls that spend credits](\u002Fdocs\u002Fchangelog\u002F2026-08-16#new-0816-3-new-402-company_budget_exhausted-rejection-on-calls-that-spend-credits)\n- 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](\u002Fdocs\u002Fchangelog\u002F2026-08-14#bc-0814-10-audio-transcription-accepts-the-file-only-in-the-file-field-never-truncates-it-silently-and-returns-a-recognition-refusal-as-400)\n- 2026-08-14 [NEW-0814-12: audio transcription can now draw on the Cowork subscription quota](\u002Fdocs\u002Fchangelog\u002F2026-08-14#new-0814-12-audio-transcription-can-now-draw-on-the-cowork-subscription-quota)\n- 2026-08-11 [FIX-0811-23: the ai_congested retry pause now scales with the configured base and is capped](\u002Fdocs\u002Fchangelog\u002F2026-08-11#fix-0811-23-the-ai_congested-retry-pause-now-scales-with-the-configured-base-and-is-capped)\n- 2026-08-06 [FIX-0806-6: speech recognition now reports a temporary provider pause](\u002Fdocs\u002Fchangelog\u002F2026-08-06#fix-0806-6-speech-recognition-now-reports-a-temporary-provider-pause)\n- 2026-08-06 [FIX-0806-7: speech recognition now really waits the stated 15 minutes](\u002Fdocs\u002Fchangelog\u002F2026-08-06#fix-0806-7-speech-recognition-now-really-waits-the-stated-15-minutes)\n- 2026-07-14 [FIX-0714-21: Transcription: wallet check before the recognition call](\u002Fdocs\u002Fchangelog\u002F2026-07-14#fix-0714-21-transcription-wallet-check-before-the-recognition-call)\n- 2026-07-10 [NEW-0710-16: AI quota pacing: pacing field in the response and 429 ai_pacing_limited error](\u002Fdocs\u002Fchangelog\u002F2026-07-10#new-0710-16-ai-quota-pacing-pacing-field-in-the-response-and-429-ai_pacing_limited-error)\n- 2026-07-06 [NEW-0706-2: New 402 error code ai_quota_exhausted on AI endpoints](\u002Fdocs\u002Fchangelog\u002F2026-07-06#new-0706-2-new-402-error-code-ai_quota_exhausted-on-ai-endpoints)\n- 2026-07-06 [FIX-0706-3: Over-quota AI usage is charged at the model's base catalog price](\u002Fdocs\u002Fchangelog\u002F2026-07-06#fix-0706-3-over-quota-ai-usage-is-charged-at-the-model-s-base-catalog-price)\n- 2026-07-05 [NEW-0705-5: New 402 error code ai_quota_exhausted on AI endpoints](\u002Fdocs\u002Fchangelog\u002F2026-07-05#new-0705-5-new-402-error-code-ai_quota_exhausted-on-ai-endpoints)\n- 2026-07-03 [NEW-0703-4: Quality and timestamp parameters in audio transcription](\u002Fdocs\u002Fchangelog\u002F2026-07-03#new-0703-4-quality-and-timestamp-parameters-in-audio-transcription)\n- 2026-06-16 [FIX-0616-2: transcription response format](\u002Fdocs\u002Fchangelog\u002F2026-06-16#fix-0616-2-transcription-response-format)\n",null,{},1794739488600]