MicrosoftDocs/azure-ai-docs/articles/ai-services

Doc: Update TTS default TPS to 30 Align with doc: https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-services-quotas-and-limits

Document VASA-2 preview avatars and upcoming avatar deprecations (#14546) * Clarify VASA-2 preview base model selection in avatar guides * Consolidate VASA-2 avatar catalog and preview assets Integrate PR #14235, address its table and wording suggestions, preserve the talking-heads bookmark, and add 512x512 previews from avatar-models. Remove VASA-2 changes from batch synthesis documentation. Co-authored-by: Melinda Ma <139100457+Melindabb@users.noreply.github.com> * Add region reference metadata requested by review * Clarify Jeff and Lisa deprecation notices in standard avatar catalog --------- Co-authored-by: Melinda Ma <139100457+Melindabb@users.noreply.github.com>

Update prebuilt analyzer document tiers Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Update 1040 analyzer contextualization tier Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Add MAI-Transcribe-2-Streaming Speech SDK language examples (#14708) * added pivot groups and code (basic compilation except Obj-C/Swift), needs further testingt * Remove redundant supported models sections from MAI streaming guides Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Move MAI-Transcribe-2-Streaming availability to overview Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Move streaming transcription language table to overview Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Fix MAI streaming Speech SDK samples Apply the sample corrections from #14720 to the Python, Java, and C# examples while preserving the additional language pivots in #14708. Co-authored-by: Kun Cong <32888804+congkun-ck@users.noreply.github.com> Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Replace additional MAI streaming SDK samples Adapt the official continuous-recognition samples for C++, JavaScript, Objective-C, and Swift, and combine the official Go file-input and continuous-recognition patterns. Add the MAI streaming model configuration consistently across all examples. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Simplify remaining MAI streaming SDK samples Use direct WAV-file inputs for JavaScript and Objective-C, and streamline the Swift recognition lifecycle. Preserve Kun's Python, Java, and C# samples and the existing C++ and Go adaptations. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Address MAI streaming documentation feedback Remove SDK pricing and unrelated technical details, use task-based pivot headings, move the session limit below the quickstart, clarify integration-specific regions, and show a compact model-specific language list. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Revert out-of-scope MAI documentation edits Restore the Realtime API limitations section and the overview's shared language include. Keep the feedback changes limited to the Speech SDK guide. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Address MAI SDK sample review feedback Add a runnable C++ entry point, dispatch Objective-C and Swift recognition off the UI thread, and replace the Swift CocoaPods prerequisite with the verified Speech SDK 1.52.0 Swift Package Manager setup. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Share SPM setup across Apple samples Reference the official Speech SDK Swift Package Manager setup from both Objective-C and Swift, using version 1.52.0 and the iOS package product. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * update regions available * remove unavailable region * add east us 2 as available --------- Co-authored-by: Emily Jiji <emilyjiji@microsoft.com> Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Co-authored-by: Kun Cong <32888804+congkun-ck@users.noreply.github.com>

Address Voice Live documentation review feedback Clarify the resource-region reference and lowercase speech data. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: 32f2663d-4104-4608-aa2a-202d7031e404

Clarify Voice Live model inference scopes Document regional model selectors and align the region, model, and pricing tables. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: 32f2663d-4104-4608-aa2a-202d7031e404

Address voice-agent documentation review feedback Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>

Improve voice-agent model selection and self-deployed samples Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>

[DocsArchive-1.0.26168.6](2026-10-05-16-07-51)Auto archive content (#14733) Co-authored-by: Docs.Archive pipeline <docsArchive@microsoft.com>

Clarify Voice Live quickstart title and move classic to Deprecated (#14728) * docs: clarify Voice Live quickstart and archive classic navigation Rename the quickstart to Voice Live with Foundry Agent Service, align title references, and move the classic integration under Deprecated without changing URLs. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> * docs: address Voice Live AI wording suggestions Use by using for SDK descriptions and present tense for the C# introduction. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Yulin Li <yulili@microsoft.com> Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>

Normalize Thai speaker language labels Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Correct Krit voice gender Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Merge pull request #14695 from lauparrs/docs/normalize-chinese-speaker-label Normalize Chinese speaker language labels

Merge pull request #14681 from meyetman/meyetman-patch-1 Meyetman patch 1

Normalize Chinese speaker language labels Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Remove styledegree from MAI Voice SSML Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

[Azure AI Svcs] Speech Audio Commit (#14629) * inline commit * update cpp * Update articles/ai-services/speech-service/includes/how-to/recognize-speech/stream-commit.md Co-authored-by: learn-build-service-prod-03[bot] <274428581+learn-build-service-prod-03[bot]@users.noreply.github.com> * Update articles/ai-services/speech-service/includes/how-to/recognize-speech/stream-commit.md Co-authored-by: learn-build-service-prod-03[bot] <274428581+learn-build-service-prod-03[bot]@users.noreply.github.com> * Update articles/ai-services/speech-service/includes/how-to/recognize-speech/stream-commit.md Co-authored-by: learn-build-service-prod-03[bot] <274428581+learn-build-service-prod-03[bot]@users.noreply.github.com> * Update articles/ai-services/speech-service/includes/how-to/recognize-speech/stream-commit.md Co-authored-by: learn-build-service-prod-03[bot] <274428581+learn-build-service-prod-03[bot]@users.noreply.github.com> * Update articles/ai-services/speech-service/includes/how-to/recognize-speech/stream-commit.md Co-authored-by: learn-build-service-prod-03[bot] <274428581+learn-build-service-prod-03[bot]@users.noreply.github.com> * resolve comments * sample link * Update articles/ai-services/speech-service/includes/how-to/recognize-speech/stream-commit.md Co-authored-by: learn-build-service-prod-07[bot] <274430390+learn-build-service-prod-07[bot]@users.noreply.github.com> * Apply suggestions from code review --------- Co-authored-by: learn-build-service-prod-03[bot] <274428581+learn-build-service-prod-03[bot]@users.noreply.github.com> Co-authored-by: learn-build-service-prod-07[bot] <274430390+learn-build-service-prod-07[bot]@users.noreply.github.com> Co-authored-by: Tracey Torble <56347952+ttorble@users.noreply.github.com>

Update WebRTC how-to for GA.md (#14660) * Update WebRTC how-to for GA.md Updated the date to 09/29/2026 and modified the endpoint URL for the Voice Live API for claiming GA * Rename 'Voice Live via WebRTC (preview)' to 'Voice Live via WebRTC' * Update voice-live-webrtc.md

Update MAI Voice documentation for 2.1 (#14617) * Update MAI Voice documentation for 2.1 Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Fix MAI Voice documentation validation Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Update MAI Voice 2.1 managed voice documentation Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Add SDK tabs to MAI Voice documentation Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Fix Türkiye locale labels Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Consolidate MAI Voice model tabs Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Move SDK samples into usage tabs Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Increase SDK sample disclosure labels Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Display SDK samples inline Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Synchronize MAI Voice model tabs across samples Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Relocate MAI Voice quickstart includes Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Add MAI Voice pricing link Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Align MAI Voice table with prompt keys Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Apply pricing style guidance Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Rerun documentation validation Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Add MAI Voice serving regions Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Use active voice for region availability Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Update MAI Voice document owner Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Align MAI Voice author metadata Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Format MAI Voice regions as a table Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Resolve MAI Voice build warnings Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Remove locale from Speech pricing link Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Remove MAI Voice GitHub author metadata Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Remove MAI Voice author metadata Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Remove MAI Voice manager metadata Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Remove preview label from MAI Voice title Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>