User Guide

Get the Most Out of VORA

From picking the right microphone to managing API costs — everything you need to run flawless AI-powered meetings.

Microphone API Keys Meeting Context Cost & Plans Pro Tips

Microphone Setup

The #1 factor in transcription accuracy is audio quality.

Important: VORA's AI correction can fix grammar and terminology errors, but it cannot recover audio that was never captured cleanly. A $30 USB mic will outperform any built-in laptop mic.

 Recommended External Microphones

Tested and ranked by the VORA team for meeting-room use. All prices are approximate USD retail (February 2026).

Model Type Best For Price Verdict
Blue Yeti X USB Condenser Solo / podcast-style desk work ~$130 Top Pick
Rode NT-USB Mini USB Condenser Solo, compact desk setup ~$100 Best Value
Jabra Speak2 55 USB Speakerphone Small meeting rooms (2–4 people) ~$200 Conference Pick
Poly Sync 20 USB Speakerphone Small meeting rooms, portable ~$150 Conference Pick
Samson Go Mic USB Clip-on Budget, travel ~$35 Budget Pick
AirPods Pro 2 / WH-1000XM5 Bluetooth Headset Noisy offices, remote worker $250–$350 Headset Pick

 Placement & Room Tips

  • Distance: Keep the mic 15–30 cm from your mouth. Too far = noise floor dominates; too close = plosives distort.
  • Angle: Point a cardioid microphone directly at your mouth, not at the ceiling or screen.
  • Room acoustics: Soft surfaces (curtains, carpets, bookshelves) absorb echo. A bare concrete room will produce noticeable reverb that confuses STT engines.
  • Background noise: Close windows, mute fans if possible. Even a laptop cooling fan at 45 dB can drop accuracy by 5–15%.
  • Bluetooth latency: Bluetooth mics add 100–200 ms of latency. VORA handles this gracefully, but wired USB is always preferable for accuracy.

 In-App Audio Settings

Open Settings → Audio Processing in VORA:

  • Noise Suppression (ON by default): Reduces background hum. Disable only if it causes artefacts on your mic.
  • Echo Cancellation (ON by default): Essential if your speakers are near the mic. Disable only for headphone-only setups where there's no echo risk.
The Web Speech API uses the microphone selected in your browser / OS audio settings. Make sure your external mic is set as the default input device before opening VORA.

API Key Setup

VORA uses your own API keys — your data stays yours.

Privacy first: API keys are stored only in your browser's localStorage. They are never sent to VORA's servers.

 Gemini API Key (Primary AI)

Gemini handles AI question detection, meeting summaries, and text correction.

1

Go to Google AI Studio

Visit aistudio.google.com → click "Get API Key""Create API key".

2

Copy the key

The key starts with AIza.... Copy it immediately — it won't be shown again in full.

3

Paste into VORA

Open Settings (⚙) → Gemini AI → API Key field. Paste and click Save.

4

Verify the status

The indicator next to the field should turn green: "Gemini Ready".

Free tier rate limit: Google's free Gemini tier allows ~15 requests/min and 1,500 requests/day. VORA's built-in priority queue manages this automatically, but long meetings (60+ min) may slow down summaries on a free key. See the Cost & Plans section.

 Groq API Key (Fast Correction)

Groq runs Llama 3.3 70B on dedicated LPU hardware — blazing fast and completely free.

1

Create a free Groq account

Visit console.groq.com → sign up → go to API Keys.

2

Generate a key

Click "Create API Key". The key starts with gsk_....

3

Paste into VORA

Open Settings → Groq Fast Correction → API Key. Paste the key.

4

Enable Fast Mode

Toggle "Enable fast dual AI mode". VORA now sends every correction request to Groq first (≈300 ms) and falls back to Gemini for summaries.

Groq free limits: ~30 requests/min, 14,400 req/day for Llama 3.3 70B. More than enough for continuous meeting use. No credit card required.

 OpenRouter API Key (Labs Only)

Used in the OpenRouter Parallel Lab to call three free LLMs simultaneously.

1

Create an OpenRouter account

Visit openrouter.ai → sign up → go to Keys.

2

Generate a key

Click "Create Key". The key starts with sk-or-....

3

Paste into the Lab

In the OpenRouter Parallel Lab page, enter your key in the API Key field at the top.

OpenRouter free tier: 20 req/min per model, 200 req/day per model with ≥$10 credits (or 50 req/day without). The lab uses models priced at $0/token.

Meeting Context Settings

Context is the single biggest accuracy lever after microphone quality.

Why Context Matters

The AI corrector receives your speech transcript as raw text. Without context it must guess whether "프로포폴" is a drug name or a mishearing of "프로포절" (proposal). With the right context it gets it right every time.

VORA injects your context into every correction and summary prompt, behaving exactly like telling a human note-taker "this is a pharmaceutical regulatory meeting — watch for these terms."

 Meeting Topic / Project Name

Found in Settings → Meeting Context → Topic / Project Name.

Write 1–3 sentences describing:

  • What industry or domain the meeting is about
  • The specific project or product being discussed
  • Any key participants or roles
Example — Pharma meeting:
"Q2 regulatory review for Phase III clinical trial of compound XR-441. Participants: medical writers, regulatory affairs team. Key focus: FDA submission timeline and adverse event classification."
Example — Tech meeting:
"Sprint planning for VORA v3.0 frontend refactor. Stack: React 19, TypeScript, Cloudflare Pages. Discuss: WebGPU rollout, Groq integration, A/B test results."

 Priority Terms

Found in Settings → Meeting Context → Priority Terms.

Enter a comma-separated list of proper nouns, acronyms, product names, or technical terms that the AI should recognise and preserve exactly:

XR-441, NDA, CDER, 부작용 분류, Phase III, ICH Q9, REMS
Cloudflare Pages, WebGPU, SentenceTransformer, RAG pipeline, 벡터 DB
  • Up to 30–40 terms work best. Too many dilute the signal.
  • Mix Korean and English freely — the model handles both.
  • Include common mis-transcriptions the system makes (e.g. "안드로이드" → "Android").
Session learning: VORA automatically learns new terms from corrections you approve during a session and adds them to the dynamic dictionary — no manual update needed.

 Meeting Category

Select the closest category in Settings → Meeting Category. This applies a pre-tuned persona to the AI:

  • General — balanced correction, no domain bias
  • IT / Software — tech terms, English-Korean code-switching
  • Medical / Pharma — clinical terminology, drug names
  • Legal — formal Korean / legal clauses
  • Finance — financial jargon, numerical precision
  • Marketing — brand names, campaign language

Cost & Plan Warnings

Understand your API costs before a long meeting.

Read before your first meeting: VORA itself is 100% free and open. However, the AI correction features use your API keys. Free tiers have hard rate limits — they do not charge you money, but they will silently throttle or stop corrections once the limit is hit.

Gemini API — Free vs Paid

 Free Tier (no card)

  • 15 requests / minute
  • 1,500 requests / day
  • 1 million tokens / minute
  • Works well for short meetings (<30 min)
  • Data may be used for model training
  • Summaries may slow after 60 min

 Pay-as-you-go ($5 minimum)

  • 2,000 requests / minute
  • Virtually unlimited daily quota
  • Data not used for training
  • SLA uptime guarantee
  • Needed for multi-hour sessions
  • ~$0.001–0.005 / correction call
Sensitive data warning: If your meeting contains confidential business information, trade secrets, or personal health data, use a paid Gemini plan to ensure Google's data-protection commitments apply. Free-tier data may be reviewed by Google staff.

Groq API — Free Tier Limits

ModelReq / MinReq / DayTokens / Min
Llama 3.3 70B Versatile (default)3014,4006,000
Llama 3.1 8B Instant3014,40020,000
Llama 3 8B 81923014,40020,000

For a typical 60-minute meeting with corrections every 3–5 seconds, VORA generates ~600–800 Groq requests — well within the 14,400/day limit.

Groq is completely free — no credit card, no paid tier required. It is the recommended fast-correction provider for all meeting sizes.

OpenRouter — Free Model Limits

Free models on OpenRouter are subject to:

  • 20 requests / minute per model
  • 200 requests / day per model (with ≥$10 credits on your account)
  • 50 requests / day per model (no credits / new account)

The OpenRouter Lab is intended for experimentation, not continuous 60-minute meetings. Use Groq for production correction and OpenRouter for side-by-side model comparison.

 Estimated Monthly Cost Examples

Usage ScenarioGemini calls/moEst. cost
2× weekly 30-min meetings, free tier~960$0 (free tier)
Daily 60-min meeting, free tier~18,000May hit daily limit
Daily 60-min meeting, paid tier~18,000~$0.10–0.50
Full workday (8 h/day), paid tier~144,000~$1–4

Pro Tips & Troubleshooting

Common issues and quick fixes from the VORA team.

🎙️ Speech not being recognised?

  • Check that your browser has microphone permission (click the lock icon in the URL bar).
  • Open your OS audio settings and confirm the correct mic is set as default input.
  • Try Chrome or Edge — the Web Speech API has the best support in Chromium browsers. Firefox and Safari have limited support.
  • Reload the page and grant mic permission again if the indicator stays red.

🤖 AI correction not working?

  • Open Settings and check the API status indicator — it should be green.
  • If it shows "API key not set", re-enter your key and save.
  • If it shows a 429 error, you've hit the rate limit. Wait 60 seconds or switch to Groq fast mode.
  • Free tier Gemini keys from newly created Google accounts may be geo-restricted. Try creating the key on a desktop browser rather than mobile.

📝 Correction quality is poor?

  • Fill in the Meeting Context and Priority Terms fields. This is the single biggest improvement lever.
  • Select the correct Meeting Category (e.g., "Medical" for clinical meetings).
  • Use the Language Selector to set the primary recognition language. Mixed Korean/English meetings should use ko-KR as the primary language.
  • Reduce the Correction Interval to 2–3 seconds for fast-paced conversations; increase to 8–10 seconds for slower, deliberate speech to save API calls.

📊 Summary is missing or empty?

  • Summaries require at least 50 words of transcript. Short meetings may not generate a summary automatically.
  • Click Export Minutes manually to force a summary generation at any time.
  • Ensure your Gemini key has remaining quota — Groq cannot generate summaries (correction only).

⌨️ Keyboard Shortcuts

ShortcutAction
Alt + RStart recording
Alt + PPause / resume recording
Alt + SStop recording
Alt + EExport meeting minutes
EscapeClose settings modal