{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"vscode-ms-vscode-vscode-speech","slug":"vs-code-speech","name":"VS Code Speech","type":"extension","url":"https://marketplace.visualstudio.com/items?itemName=ms-vscode.vscode-speech","page_url":"https://unfragile.ai/vs-code-speech","categories":["code-editors"],"tags":["a11y","Accessibility","ai","Chat","co-pilot","Microsoft","multi-root ready","STT","transcription","voice"],"pricing":{"model":"freemium","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"vscode-ms-vscode-vscode-speech__cap_0","uri":"capability://text.generation.language.voice.to.text.chat.input.with.hold.to.submit","name":"voice-to-text chat input with hold-to-submit","description":"Captures microphone audio during active chat sessions and transcribes it to text using Azure Speech SDK, with configurable language selection and automatic submission on release. Integrates directly into GitHub Copilot Chat UI via a microphone button, supporting both continuous listening and push-to-talk modes via Ctrl+I (Windows/Linux) or Cmd+I (macOS). The extension handles audio buffering, language detection, and real-time transcription without requiring API keys or internet connectivity for local processing.","intents":["I want to ask Copilot questions using my voice instead of typing in the chat","I need hands-free interaction with AI chat while coding or multitasking","I want to use voice input for accessibility reasons while maintaining chat context"],"best_for":["developers with accessibility needs (RSI, mobility constraints)","solo developers seeking faster code exploration via voice queries","teams using GitHub Copilot Chat as primary AI assistant"],"limitations":["Requires GitHub Copilot Chat extension installed; chat voice features unavailable without it","Language support limited to 26 languages (specific list not enumerated in documentation)","No multi-turn voice conversation without manual re-triggering between exchanges","Transcription accuracy depends on microphone quality and ambient noise; no noise cancellation documented","Azure Speech SDK dependency suggests potential cloud fallback behavior not explicitly documented"],"requires":["VS Code (minimum version not specified)","GitHub Copilot Chat extension installed","Microphone hardware with OS-level permission granted","macOS: Privacy & Security settings must explicitly allow microphone access","Linux: ALSA shared library (libasound) installed"],"input_types":["audio stream (microphone input)","language selection (via accessibility.voice.speechLanguage setting)"],"output_types":["transcribed text (inserted into chat input field)","chat submission trigger"],"categories":["text-generation-language","accessibility"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"vscode-ms-vscode-vscode-speech__cap_1","uri":"capability://code.generation.editing.editor.dictation.with.cursor.position.insertion","name":"editor dictation with cursor-position insertion","description":"Enables voice-to-text input directly into the active editor at the current cursor position via Ctrl+Alt+V (Windows/Linux) or Cmd+Alt+V (macOS). Uses Azure Speech SDK for transcription with configurable language selection. Text is inserted synchronously after transcription completes, supporting code comments, documentation, and prose without requiring chat context or Copilot Chat extension.","intents":["I want to dictate code comments and docstrings without typing","I need to write documentation or prose in the editor using voice","I want to use voice input for accessibility while editing code"],"best_for":["developers with accessibility needs (RSI, mobility constraints)","technical writers documenting code via voice","developers seeking faster documentation generation"],"limitations":["Insertion point fixed to current cursor position; no multi-location or batch insertion","No context awareness of code structure (e.g., cannot auto-format as code vs. comment)","Standalone feature independent of Copilot Chat; no AI-assisted editing or correction","Language support limited to 26 languages (specific list not enumerated)","Transcription accuracy depends on microphone quality; no built-in error correction or undo-on-error"],"requires":["VS Code (minimum version not specified)","Microphone hardware with OS-level permission granted","macOS: Privacy & Security settings must explicitly allow microphone access","Linux: ALSA shared library (libasound) installed","GitHub Copilot Chat extension NOT required for this feature"],"input_types":["audio stream (microphone input)","language selection (via accessibility.voice.speechLanguage setting)","cursor position in active editor"],"output_types":["transcribed text (inserted at cursor position in editor)"],"categories":["code-generation-editing","accessibility"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"vscode-ms-vscode-vscode-speech__cap_10","uri":"capability://tool.use.integration.development.stage.extension.with.ongoing.feature.evolution","name":"development-stage extension with ongoing feature evolution","description":"The extension is explicitly documented as 'still in development,' indicating active feature development, bug fixes, and potential breaking changes. The extension is distributed via the VS Code Marketplace as a free, installable extension, but stability, maturity, and feature completeness are not guaranteed. Users should expect changes to keybindings, settings, UI, and capabilities as the extension evolves.","intents":["I want to try early-stage voice capabilities and provide feedback to the development team","I need to understand the maturity and stability of this extension before adopting it in production","I want to contribute to or follow the development of voice features in VS Code"],"best_for":["early adopters willing to tolerate breaking changes and bugs","developers seeking to provide feedback on voice features","teams evaluating voice capabilities before they reach stable release"],"limitations":["Stability not guaranteed; bugs, crashes, and data loss are possible","Keybindings, settings, and UI may change without notice; custom configurations may break","Feature completeness unknown; documented features may be incomplete or partially implemented","Performance characteristics (latency, CPU/memory overhead) not optimized; may be slower than stable alternatives","No documented roadmap, release schedule, or feature request process; unclear when features will be added or bugs fixed","No version number provided; unclear what version is currently installed or what changes were made in recent updates"],"requires":["VS Code (minimum version not specified)","Tolerance for breaking changes and bugs","Willingness to report issues and provide feedback to the development team"],"input_types":["none (development status is inherent to the extension)"],"output_types":["voice capabilities (subject to change)"],"categories":["tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"vscode-ms-vscode-vscode-speech__cap_2","uri":"capability://text.generation.language.automatic.text.to.speech.synthesis.of.chat.responses","name":"automatic text-to-speech synthesis of chat responses","description":"Reads chat responses aloud using text-to-speech synthesis when the `accessibility.voice.autoSynthesize` setting is enabled AND the user initiated the chat message via voice input. The extension uses Azure Speech SDK for TTS with language selection matching the STT language. Audio playback occurs automatically after the AI response is generated, providing audio feedback without requiring manual activation.","intents":["I want to hear Copilot's responses read aloud when I use voice input","I need audio feedback for accessibility reasons while using voice chat","I want to multitask while listening to AI responses instead of reading them"],"best_for":["developers with visual impairments or accessibility needs","developers multitasking or unable to read screen output","teams using voice-first interaction patterns with Copilot Chat"],"limitations":["TTS only activates when voice was used as input; text-only chat queries do not trigger audio output","TTS scope limited to chat responses; cannot read arbitrary editor text or code","Language support limited to 26 languages; TTS voice selection not documented as user-configurable","No control over TTS playback speed, pitch, or voice selection documented","Automatic synthesis may interrupt workflow if responses are lengthy; no pause/resume controls documented"],"requires":["VS Code (minimum version not specified)","GitHub Copilot Chat extension installed","accessibility.voice.autoSynthesize setting enabled","Voice input used to initiate the chat message (STT must be active)","Audio output device (speakers or headphones) with working audio drivers"],"input_types":["chat response text (from AI model)","language selection (via accessibility.voice.speechLanguage setting)"],"output_types":["audio stream (TTS synthesis to speakers/headphones)"],"categories":["text-generation-language","accessibility"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"vscode-ms-vscode-vscode-speech__cap_3","uri":"capability://text.generation.language.multi.language.speech.recognition.and.synthesis","name":"multi-language speech recognition and synthesis","description":"Supports speech-to-text and text-to-speech across 26 languages via the `accessibility.voice.speechLanguage` setting, which applies uniformly to both STT and TTS operations. Language selection is configurable via VS Code's Settings Editor and persists across sessions. The extension uses Azure Speech SDK's language models for both recognition and synthesis, with language detection and processing handled transparently without user intervention.","intents":["I want to use voice input and output in my native language, not English","I need to switch between languages for different projects or team contexts","I want to dictate code comments in a language other than English"],"best_for":["international development teams using non-English languages","developers working in multilingual codebases","non-English speakers seeking accessibility features in their native language"],"limitations":["Language support limited to 26 languages; specific supported languages not enumerated in documentation","Single language selection applies globally to both STT and TTS; no per-session or per-file language switching","Language pack installation mechanism not documented; may require additional VS Code extensions","Transcription accuracy varies by language; no language-specific tuning or custom vocabulary support documented","TTS voice selection per language not documented as user-configurable"],"requires":["VS Code (minimum version not specified)","Language selection via accessibility.voice.speechLanguage setting","Microphone and audio output devices (for respective STT/TTS operations)"],"input_types":["language code or name (via accessibility.voice.speechLanguage setting)","audio stream (microphone input for STT)"],"output_types":["transcribed text in selected language","audio stream (TTS synthesis in selected language)"],"categories":["text-generation-language","accessibility"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"vscode-ms-vscode-vscode-speech__cap_4","uri":"capability://automation.workflow.keybinding.driven.voice.session.control","name":"keybinding-driven voice session control","description":"Provides keyboard shortcuts to start, stop, and submit voice input sessions without mouse interaction. Default keybindings are Ctrl+I (Windows/Linux) or Cmd+I (macOS) for chat voice (hold-to-submit or toggle mode), and Ctrl+Alt+V (Windows/Linux) or Cmd+Alt+V (macOS) for editor dictation. Keybindings are fully customizable via VS Code's Keybinding Shortcuts Editor, with conditional activation via `when` clauses (e.g., `!voiceChatInProgress`, `!editorDictation.inProgress`) to prevent conflicts.","intents":["I want to start and stop voice input using keyboard shortcuts, not mouse clicks","I need to customize voice keybindings to match my existing VS Code workflow","I want to prevent accidental voice activation by using conditional keybindings"],"best_for":["developers with accessibility needs (mobility constraints, RSI)","power users seeking keyboard-only workflows","teams standardizing voice keybindings across VS Code instances"],"limitations":["Default keybindings may conflict with existing user keybindings; manual resolution required","Conditional keybindings limited to voice-specific contexts (`voiceChatInProgress`, `editorDictation.inProgress`); no integration with broader editor state (e.g., debugging, terminal focus)","Keybinding customization requires manual editing of keybindings.json; no UI-based keybinding wizard documented","No macro or multi-step keybinding support (e.g., start voice, wait for input, auto-submit after silence)"],"requires":["VS Code (minimum version not specified)","Keybinding Shortcuts Editor (built-in to VS Code)","Knowledge of VS Code keybinding syntax and `when` clause conditions"],"input_types":["keyboard input (keybinding trigger)","keybinding configuration (via keybindings.json or Settings Editor)"],"output_types":["voice session state change (start/stop/submit)","audio input capture (microphone activation)"],"categories":["automation-workflow","accessibility"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"vscode-ms-vscode-vscode-speech__cap_5","uri":"capability://text.generation.language.local.speech.processing.with.azure.speech.sdk","name":"local speech processing with azure speech sdk","description":"Processes speech-to-text and text-to-speech operations using Azure Speech SDK, which the extension claims performs local processing on the user's machine without requiring internet connectivity or API keys. The SDK handles audio capture, buffering, language detection, and transcription/synthesis internally. However, the documentation does not explicitly clarify whether Azure Speech SDK calls are truly local or cloud-based, creating ambiguity about data privacy and network requirements.","intents":["I want to use voice input without sending audio data to cloud services","I need voice capabilities without managing API keys or cloud service accounts","I want to ensure my voice data remains on my local machine for privacy"],"best_for":["developers with strict data privacy requirements","teams operating in air-gapped or offline environments","users seeking voice capabilities without cloud service dependencies"],"limitations":["Azure Speech SDK dependency suggests potential cloud fallback behavior not explicitly documented; local-only processing claim is unverified","No explicit offline mode or fallback mechanism documented; behavior when network is unavailable is unknown","No option to use alternative STT/TTS engines (e.g., local Whisper, Coqui) or cloud providers (Google, AWS)","Audio format support and codec compatibility not documented","Performance characteristics (latency, CPU/memory overhead) not documented; local processing may have higher resource requirements than cloud alternatives"],"requires":["VS Code (minimum version not specified)","Azure Speech SDK (bundled with extension; no separate installation required)","Microphone and audio output devices","macOS: Privacy & Security settings must explicitly allow microphone access","Linux: ALSA shared library (libasound) installed"],"input_types":["audio stream (microphone input)","text (for TTS synthesis)"],"output_types":["transcribed text (STT output)","audio stream (TTS output)"],"categories":["text-generation-language","safety-moderation"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"vscode-ms-vscode-vscode-speech__cap_6","uri":"capability://tool.use.integration.github.copilot.chat.ui.integration.with.microphone.button","name":"github copilot chat ui integration with microphone button","description":"Embeds a microphone button directly into the GitHub Copilot Chat interface, providing visual affordance for voice input without requiring keybinding knowledge. The button appears in the chat input area and triggers voice capture when clicked or held, with visual feedback indicating recording state. Integration is seamless when both VS Code Speech and GitHub Copilot Chat extensions are installed; the microphone button is unavailable if Copilot Chat is not present.","intents":["I want to see a visible microphone button in the chat interface to start voice input","I need visual feedback that voice recording is active while I'm speaking","I want to use voice chat without memorizing keybindings"],"best_for":["users new to voice input seeking discoverable UI affordances","developers preferring mouse/click interaction over keybindings","teams with mixed accessibility needs (some users prefer visual buttons, others prefer keybindings)"],"limitations":["Microphone button only appears in GitHub Copilot Chat UI; not available in other chat interfaces or extensions","Button visibility depends on GitHub Copilot Chat extension being installed; no fallback UI if Copilot Chat is unavailable","Visual feedback (recording state indicator) design and clarity not documented","No customization of button appearance, position, or behavior documented","Button may be obscured or difficult to access on small screens or with certain VS Code layouts"],"requires":["VS Code (minimum version not specified)","GitHub Copilot Chat extension installed and enabled","Mouse or touch input device (for clicking/tapping microphone button)"],"input_types":["mouse click or touch input (on microphone button)","audio stream (microphone input after button activation)"],"output_types":["visual feedback (recording state indicator)","transcribed text (inserted into chat input field)"],"categories":["tool-use-integration","accessibility"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"vscode-ms-vscode-vscode-speech__cap_7","uri":"capability://tool.use.integration.cross.platform.voice.support.with.os.specific.permission.handling","name":"cross-platform voice support with os-specific permission handling","description":"Provides voice capabilities across Windows (x64/ARM), macOS (x64/ARM), and Linux (x86/x64/ARM32/ARM64) with platform-specific microphone permission handling. On macOS, users must explicitly grant microphone access via Privacy & Security settings; on Windows and Linux, permission mechanisms are not documented. Linux support requires ALSA shared library (libasound) installation. The extension abstracts platform differences via Azure Speech SDK, presenting a unified voice API across all platforms.","intents":["I want to use voice input on my Windows, macOS, or Linux machine","I need to understand how to grant microphone permissions on my OS","I want voice capabilities that work consistently across my team's diverse hardware"],"best_for":["cross-platform development teams using Windows, macOS, and Linux","developers seeking voice capabilities on non-macOS systems","teams with ARM-based machines (Apple Silicon, Raspberry Pi, etc.)"],"limitations":["Linux support requires manual ALSA library installation; no automatic dependency resolution documented","Linux distributions supported limited to Ubuntu 20.04/22.04/24.04, Debian 11/12, RHEL 8, CentOS 8; other distributions may not work","Windows and Linux microphone permission mechanisms not documented; users must infer OS-level permission steps","ARM support (Windows ARM, macOS ARM, Linux ARM32/ARM64) may have different performance characteristics or limitations not documented","Cross-platform testing and bug reporting mechanisms not documented; platform-specific issues may be harder to diagnose"],"requires":["VS Code (minimum version not specified)","Windows: x64 or ARM architecture","macOS: x64 or ARM architecture; Privacy & Security settings must explicitly allow microphone access","Linux: Ubuntu 20.04+, Debian 11+, RHEL 8+, or CentOS 8+; ALSA shared library (libasound) installed","Microphone hardware with working audio drivers"],"input_types":["audio stream (microphone input)","OS-level microphone permission (granted via OS settings)"],"output_types":["transcribed text (STT output)","audio stream (TTS output)"],"categories":["tool-use-integration","accessibility"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"vscode-ms-vscode-vscode-speech__cap_8","uri":"capability://automation.workflow.voice.session.state.management.with.conditional.keybindings","name":"voice session state management with conditional keybindings","description":"Tracks voice session state (active/inactive) for both chat voice and editor dictation, exposing state via `when` clause conditions (`voiceChatInProgress`, `editorDictation.inProgress`) that can be used in keybindings to prevent conflicts or trigger conditional actions. The extension manages state transitions (start, recording, stop, submit) internally and prevents simultaneous voice sessions across chat and editor contexts.","intents":["I want to prevent accidental voice activation by using conditional keybindings that check if voice is already active","I need to know when voice recording is in progress so I can avoid interrupting it","I want to create keybindings that behave differently depending on whether voice is active"],"best_for":["power users building complex keybinding configurations","teams standardizing voice workflows with conditional logic","developers seeking to prevent voice session conflicts"],"limitations":["State conditions limited to voice-specific contexts; no integration with broader editor state (debugging, terminal focus, file modified status)","No programmatic API to query or manipulate voice state; state is only accessible via `when` clauses in keybindings","No state persistence across VS Code sessions; voice state is reset on extension reload or VS Code restart","No event hooks or callbacks for voice state changes; extensions cannot react to voice session start/stop events","Simultaneous voice session prevention is implicit; no explicit configuration or error handling for attempted concurrent sessions"],"requires":["VS Code (minimum version not specified)","Knowledge of VS Code `when` clause syntax and condition evaluation","Keybinding configuration via keybindings.json or Settings Editor"],"input_types":["voice session state (internal to extension)","keybinding condition evaluation (from VS Code)"],"output_types":["boolean state value (for `when` clause evaluation)","keybinding activation/deactivation (based on state)"],"categories":["automation-workflow","accessibility"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"vscode-ms-vscode-vscode-speech__cap_9","uri":"capability://tool.use.integration.freemium.licensing.with.free.core.voice.features","name":"freemium licensing with free core voice features","description":"Offers voice-to-text and text-to-speech capabilities at no cost via the free tier, with no documented premium tier or paid features. The extension is distributed via the VS Code Marketplace as a free, open-to-install extension with no license key, subscription, or payment requirement. Pricing model is freemium, but the premium tier (if any) is not documented.","intents":["I want to use voice input and output in VS Code without paying for a subscription","I need to evaluate voice capabilities before committing to a paid tool","I want to use voice accessibility features without cost barriers"],"best_for":["individual developers and hobbyists seeking free voice capabilities","teams evaluating voice tools before purchasing premium alternatives","accessibility-focused users seeking free voice features"],"limitations":["Premium tier features (if any) not documented; unclear what (if any) paid features exist","Free tier limitations not explicitly documented; unclear if there are usage quotas, language restrictions, or feature limitations","Dependency on GitHub Copilot Chat for chat voice features may require Copilot subscription (not part of VS Code Speech pricing)","Azure Speech SDK usage may incur cloud costs if processing is cloud-based (not documented)","No documented SLA, support tier, or service level guarantees for free tier"],"requires":["VS Code (minimum version not specified)","Free installation from VS Code Marketplace (no license key required)"],"input_types":["none (free tier is automatically available)"],"output_types":["voice capabilities (STT, TTS, chat integration, editor dictation)"],"categories":["tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":49,"verified":false,"data_access_risk":"high","permissions":["VS Code (minimum version not specified)","GitHub Copilot Chat extension installed","Microphone hardware with OS-level permission granted","macOS: Privacy & Security settings must explicitly allow microphone access","Linux: ALSA shared library (libasound) installed","GitHub Copilot Chat extension NOT required for this feature","Tolerance for breaking changes and bugs","Willingness to report issues and provide feedback to the development team","accessibility.voice.autoSynthesize setting enabled","Voice input used to initiate the chat message (STT must be active)"],"failure_modes":["Requires GitHub Copilot Chat extension installed; chat voice features unavailable without it","Language support limited to 26 languages (specific list not enumerated in documentation)","No multi-turn voice conversation without manual re-triggering between exchanges","Transcription accuracy depends on microphone quality and ambient noise; no noise cancellation documented","Azure Speech SDK dependency suggests potential cloud fallback behavior not explicitly documented","Insertion point fixed to current cursor position; no multi-location or batch insertion","No context awareness of code structure (e.g., cannot auto-format as code vs. comment)","Standalone feature independent of Copilot Chat; no AI-assisted editing or correction","Language support limited to 26 languages (specific list not enumerated)","Transcription accuracy depends on microphone quality; no built-in error correction or undo-on-error","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.82,"quality":0.32,"ecosystem":0.35000000000000003,"match_graph":0.25,"freshness":0.75,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.15,"match_graph":0.23,"freshness":0.12}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:34.803Z","last_scraped_at":"2026-05-03T15:20:29.937Z","last_commit":null},"community":{"stars":null,"forks":null,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=vs-code-speech","compare_url":"https://unfragile.ai/compare?artifact=vs-code-speech"}},"signature":"37lwTkjT0W00/F5ph3X99lJmQKQCqbAx5j/RfbX6IobBUT3r/Kz7a/SJUWGLyM6UskV3itkgYcI4rxT7iLsQDA==","signedAt":"2026-06-20T14:28:19.135Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/vs-code-speech","artifact":"https://unfragile.ai/vs-code-speech","verify":"https://unfragile.ai/api/v1/verify?slug=vs-code-speech","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}