Audio & Speech (TTS / STT)

The Audio & Speech suite in Snipset integrates high-performance Speech-to-Text (STT) voice dictation and Text-to-Speech (TTS) Read Aloud capabilities directly into your desktop workflow. Designed with a local-first privacy focus, it operates across any active Windows application, text field, code editor, or browser with minimal latency.

Key Capabilities

• Multi-Mode Speech-to-Text (STT): Dictate text directly at your cursor, translate speech into foreign languages on the fly, or speak natural prompts directly to AI models (Ask Anything).
• Continuous Dictation & Pause-Resilience: Speak at your natural pace with zero transcription loss during thinking pauses, silence gaps, or window focus shifts.
• Post-Hoc Keystroke Correction & Automated Learning: Tracks manual keyboard edits after dictation to calculate real-time edit rates and automatically suggest learned vocabulary for your custom dictionary.
• Global Read Aloud (TTS): Highlight any text in any Windows app and press your configured hotkey (Alt+I by default; alias CommandOrControl+Alt+R) to listen via natural voice synthesis.
• TTS Feedback for AI Responses: Listen to generated AI answers directly inside the floating speech overlay with full playback controls.
• Hardware Audio Optimization: Automatic Gain Control (AGC), Noise Suppression, Acoustic Echo Cancellation (AEC), and silence threshold tuning.
• Local Whisper & Offline Mode: Transcribe audio entirely on-device using optimized Whisper ONNX models with zero data telemetry.
• Personalized Speech Dictionary: Define custom acronyms, code symbols, and technical jargon to eliminate transcription errors.
• Voice Profiles & Custom Voices: Choose between system SAPI5, Edge neural voices, local Sherpa-ONNX engines, or custom cloned voice profiles.
• Privacy & Retention Guardrails: Configurable auto-purge periods for audio recordings and single-click history deletion.
• Productivity & Speech Analytics: Track words dictated, characters read aloud, edit distance rates, and time saved in the Statistics dashboard.

---

Getting Started

Access the Audio & Speech settings from Settings → Audio & Voice in the Snipset sidebar:

+-------------------------------------------------------------+
| 🎙️ Active Microphone: [ HyperX QuadCast S (Default)       ] |
| ⚡ Audio Preset:     [ ● Close-field USB Mic  ○ Laptop Mic ] |
| 🔊 Hardware Filters:  [✔] AGC   [✔] Noise Suppression [✔] AEC|
+-------------------------------------------------------------+
| 📝 Dictation Hotkey:  [ Alt+.  (alias: CommandOrControl+Alt+D) ] |
| 🗣️ Read Aloud Hotkey: [ Alt+I  (alias: CommandOrControl+Alt+R) ] |
| 🌐 Primary Language:  [ English (United States)          ▼ ] |
+-------------------------------------------------------------+
| 🤖 Whisper Model:     [ Whisper Base (Local ONNX)        ▼ ] |
| 🔊 TTS Engine:        [ Microsoft Natural Edge (Auto)    ▼ ] |
+-------------------------------------------------------------+

---

Speech-to-Text (STT) & Dictation Modes

Snipset supports three distinct voice input modes mapped to your preferred triggers:

1. Direct Dictation (dictate)

Hold (Push-to-Talk) or press (Toggle) your dictation shortcut, speak naturally, and release. Snipset transcribes your voice in real time and automatically types the text at your active cursor position.

• Continuous Text Retention: Speaking pauses and thinking breaks do not cause premature timeouts. Your live transcript accumulates safely across multiple speech segments.
• Punctuation & Capitalization: Automatically normalizes punctuation ("comma", "period", "new line").
• Cursor Injection: Uses low-level Windows input synthesis to paste directly into IDEs, command prompts, chat apps, and browser forms.

2. Live Voice Translation (translate)

Speak in your native language (e.g. Indonesian, Spanish, Japanese), and Snipset automatically transcribes and outputs the translated text into your chosen target language (e.g. English) in real time.

3. Voice AI: Ask Anything (ask_anything)

Speak complex questions or coding instructions. Snipset captures your voice, converts it to structured text, forwards it to your active local Ollama model or Cloud AI assistant, and displays the response in the overlay card with immediate text insertion and Read Aloud audio playback options.

---

Post-Hoc Keystroke Learning & Edit Rate

Snipset features an intelligent background feedback loop that learns from how you edit dictated text:

• 15-Second Edit Window: Following a dictation session, Snipset monitors manual keyboard edits and backspaces in the target application.
• Real-Time Edit Rate Evaluation: Calculates the Levenshtein edit distance between the original transcription and your finalized text.
• Automated Dictionary Proposals: When you manually correct a misrecognized technical term (e.g., changing "cubernetis" to "Kubernetes"), Snipset flags the pair and offers one-click addition to your Custom Speech Dictionary.

---

Floating Speech Overlay HUD

When recording, an unobtrusive floating HUD appears over your screen:

• Live VU Meter & Waveform: Real-time visualization of your microphone input level.
• State Indicators: Visual feedback for Listening, Transcribing, Synthesizing, and Editing.
• AI Response Card with TTS: In Ask Anything mode, view the streaming AI response card with dedicated Play, Pause, Resume, Stop, and Copy buttons.
• Audio Feedback Soundpacks: Optional audio cues (soft chimes) confirming when recording starts, stops, or succeeds.

---

Text-to-Speech (TTS) & Read Aloud

The Read Aloud engine lets you listen to lengthy documents, pull request diffs, emails, or snippets without eyestrain.

Triggering Read Aloud

1. Highlight Text: Select text in any window (VS Code, Chrome, Outlook, Notion).
2. Global Shortcut: Press Alt+I (alias CommandOrControl+Alt+R, or your configured hotkey).
3. Playback Overlay: Control playback (Play, Pause, Resume, Stop) from the HUD or media hotkeys. Also available as Read Aloud & RSVP Shortcut in Settings → Audio & Voice.

Multi-Engine Architecture

Snipset features a resilient multi-engine TTS pipeline:

Engine Mode	Description	Latency	Internet Requirement
Auto (Recommended)	Uses natural cloud voices when online, falling back to local engines when offline.	Ultra-low	Optional
Local Only (SAPI5 / Sherpa)	Synthesizes speech locally using Windows SAPI5 or offline Kokoro/Sherpa-ONNX models.	Instant	100% Offline
Edge Neural / Cloud	High-fidelity natural human speech synthesis with nuanced intonation across 70+ languages.	Low	Required

Voice Profiles & Playback Tuning

• Speed & Pitch: Adjust speech velocity from 0.5x to 2.5x with real-time slider controls.
• Voice Customization: Switch between distinct male and female voice personas per language.
• Persistent Audio Caching: Synthesized audio chunks are cached locally on disk. Re-reading identical text plays instantly without reprocessing.

---

Personalized Speech Dictionary

Specialized industry terminology, library names, and code identifiers (e.g., Kubernetes, PostgreSQL, Axios, OAuth2) can sometimes be misheard by general acoustic models.

Snipset provides a Custom Speech Dictionary:

1. Open Settings → Audio & Voice → Custom Dictionary (also Settings → Audio & Voice shows Personalized Speech Dictionary).
2. Add a Trigger Word (how it sounds) and the Replacement Text (how it should be typed).
3. Auto-Dictionary Learning: View learned suggestions generated from your post-hoc keyboard corrections and approve them with a single click.

---

Hardware Audio Preprocessing

To guarantee optimal accuracy regardless of your environment, Snipset includes built-in DSP (Digital Signal Processing) audio filters:

• Automatic Gain Control (AGC): Dynamically adjusts input volume so whisper-quiet and loud speech are leveled equally.
• Noise Suppression: Removes background HVAC hum, keyboard clicks, computer fans, and ambient room noise.
• Acoustic Echo Cancellation (AEC): Prevents audio coming from your desktop speakers from triggering microphone loops.
• Distance Presets:
  • Laptop / Webcam Mic: High-gain profile tuned for distance (1–2 meters).
  • USB / Headset Mic: Low-gain, close-proximity profile optimized for clarity.

---

Privacy, Security & Data Retention

Snipset is engineered around strict data confidentiality:

• Zero Cloud Recording Option: When using Local Whisper ONNX models, audio never leaves your local machine.
• Retention Policies: Configure automatic audio file purge rules (7 days, 30 days, 90 days, or Never).
• Encrypted Local Storage: Voice history logs and temporary WAV files are stored in your private local app data directory.
• One-Click Purge: Delete all cached audio recordings instantly via Settings → Audio & Voice → Purge All Recordings (and per-entry purge in Speech History).

---

Configuration Reference

Configuration Key	Type	Default	Description
dictation_hotkey	String	"Alt+." (alias CommandOrControl+Alt+D)	Global shortcut to start/stop Speech-to-Text dictation. Other speech aliases: CommandOrControl+Alt+T (translate), CommandOrControl+Alt+A (ask-anything), CommandOrControl+Alt+R (read-aloud).
read_aloud_hotkey	String	"Alt+I" (alias CommandOrControl+Alt+R)	Global shortcut to trigger Text-to-Speech Read Aloud.
stt_model	String	"whisper-base"	Active acoustic speech recognition model.
primary_language	String	"en-US"	Primary spoken language for dictation.
translation_target_lang	String	"en"	Target language when using Live Voice Translation.
post_hoc_learning	Boolean	true	Enable automated vocabulary learning from post-dictation keystroke edits.
auto_gain_control	Boolean	true	Enable hardware automatic volume gain normalization.
noise_suppression	Boolean	true	Enable background noise and fan filter.
tts_engine_mode	String	"auto"	TTS engine selection (auto, local_only, browser_only).
tts_speed	Number	1.0	Read Aloud speech playback rate multiplier (0.5 to 2.5).
retention_period	String	"30d"	Time to keep audio files before automated cleanup.