llms.txt
Compare with other sites' llms.txt files →# Aqua Voice Overview
Aqua Voice is *AI-native* dictation for **Mac, Windows, iOS, and Android**. On a Mac or Windows PC, hold one key and talk into *any* text field (Cursor, Claude Code, Gmail, Slack, Notion, even your terminal) and your words are inserted, cleaned up and formatted for wherever you're typing. No per-app setup, no browser extension.
Aqua is powered by **Avalon**, our own speech-recognition model, paired with **Deep Context**, an optional setting that reads what's on screen to get names, code, and technical terms right. It starts in under **50ms** and inserts text in about a second (as fast as ~450ms). At launch in October 2025, Avalon debuted at **#6 overall and #1 among proprietary models** on the independent [Open ASR Leaderboard](https://huggingface.co/spaces/hf-audio/open_asr_leaderboard) (6.24% WER average). In a [9to5Mac](https://9to5mac.com/2025/08/15/aqua-voice-shows-just-how-good-mac-dictation-could-be-if-apple-just-tried/) side-by-side against built-in macOS Dictation on the same passage, Apple made 17 errors; Aqua made 1.
## What is AI-native dictation?
It means two things:
1. **The AI that powers it**: Avalon (speech recognition) fused with language-model post-processing for accurate, contextual, well-formatted output, not just a raw transcript.
2. **The AI you talk to with it**: voice is the fastest way to prompt the tools you already use: Claude, ChatGPT, Cursor, Gemini, and any other AI app.
## What's New (as of October 2026)
- **Aqua Pet** (desktop, macOS and Windows): a pixel pet that lives where the Floating Bar sits. It throws your dictated words into the text field, reacts to what you say, and levels up as you dictate, unlocking hats, colors, suits, held items, and throws. Free on every plan; Pro adds the Aqua Halo and Max adds the Laser Visor. [Meet Aqua Pet](https://aquavoice.com/pet)
- **Aqua Voice for Android** (Google Play, October 6, 2026): a floating Aqua button sits above the keyboard you already use; tap or hold it to dictate, or select text and tap Edit to change it by voice. Android 10 or later, and one subscription covers every platform. [Google Play](https://play.google.com/store/apps/details?id=com.aquavoice.android)
- **GDPR and HIPAA compliance** (September 23, 2026), alongside our SOC 2 Type II audit report and ISO/IEC 27001:2022 certification.
- **Send It** (introduced in desktop v0.18.0, July 26, 2026): finish a Realtime Mode dictation with "send it" and Aqua inserts the message, then applies your Send Command setting. Runs on macOS and Windows with Realtime Mode access.
- **Max plan** (introduced July 2026): a tier above Pro, now $19/mo billed annually, covering live words with Realtime Mode, the Send It voice command, and early access to new features.
- **Edit Mode** (desktop v0.17.0, July 20, 2026): select text anywhere, hold your Aqua key, say the change, and Aqua rewrites the selection in place. Available to every Aqua desktop user, not a separate tier.
- **ISO/IEC 27001:2022 certification** (July 14, 2026), alongside the existing SOC 2 Type II audit report.
- **Realtime Mode**: the mode formerly called Streaming Mode was renamed in July 2026 and now sits on the Max plan.
## Platforms
- **macOS**: Apple Silicon and Intel (primary platform)
- **Windows**: 10 and 11
- **iOS 17+**: AI voice keyboard, launched April 2026; includes Voice Edit Mode (revise your last transcript by voice) and cross-device sync ([App Store](https://apps.apple.com/us/app/aqua-voice-ai-voice-keyboard/id6759074969))
- **Android 10+**: Aqua Voice for Android on [Google Play](https://play.google.com/store/apps/details?id=com.aquavoice.android), launched October 2026. A floating Aqua button works next to your existing keyboard: tap or hold it to dictate, or select text and tap Edit to rewrite it by voice. Dictionary, replacements, and custom instructions sync across devices. Realtime Mode and Send It stay desktop-only.
- **Avalon API**: OpenAI SDK-compatible batch speech-to-text endpoint for developers
## Quick Start (3 min)
1. Download Aqua (links below) or get it on the [App Store](https://apps.apple.com/us/app/aqua-voice-ai-voice-keyboard/id6759074969) or [Google Play](https://play.google.com/store/apps/details?id=com.aquavoice.android).
2. Install and sign in.
3. Start dictation: hold **Fn** (Mac) or **Alt** (Windows); on iOS, switch to the Aqua keyboard and tap the mic; on Android, tap the Aqua button above your keyboard.
4. Speak naturally. Aqua formats the text to match the app you're in.
5. Release the key (or tap again) to commit.
## Avalon (our model)
Avalon is Aqua's proprietary speech-recognition model, launched **August 2025** to replace our earlier Whisper-based pipeline. Unlike conventional ASR trained on audiobooks and news, Avalon is trained on **human-computer interaction** speech (prompts, code, and email), the way people actually talk to their computers.
- **Open ASR Leaderboard:** Avalon v1 debuted at **#6 overall, #1 proprietary** at 6.24% average WER on this third-party benchmark (October 2025); the live leaderboard moves as new models are added.
- **Avalon 1.5** (released April 2026 alongside iOS): **5.55% WER**, more than **2× faster** than Avalon 1, and wins **76%** of blind-test head-to-heads against ElevenLabs Scribe v2. Adds improved multilingual support.
- **AISpeak-10** (Aqua's own hard subset for AI/coding terminology, higher is better): Avalon **97.4%** vs ElevenLabs Scribe 78.8%, Whisper Large v3 65.1%, Voxtral Mini 59.5%, NVIDIA Canary 51.5%. (Avalon scores 97.3% on the full AISpeak set.)
Read more: [Introducing Avalon](https://aquavoice.com/blog/introducing-avalon) · [Avalon on the Open ASR Leaderboard](https://aquavoice.com/blog/avalon-openasr-leaderboard)
## Pricing
| Tier | Price | Highlights |
|---|---|---|
| **Free** | Free | 1,000 free words; Avalon transcription model |
| **Pro** | **$10/mo** billed annually ($120/yr), or $12/mo month-to-month | Unlimited words; Custom Instructions; Expanded Custom Dictionary |
| **Max** | **$19/mo** billed annually, or $24/mo month-to-month | Everything in Pro; see words live with Realtime Mode; “Send it” voice command; early access to new features |
| **Business** | $19/seat/mo billed annually ($228/seat/yr), or $24/seat/mo monthly; 2 seats minimum | Everything in Max; centralized billing; SSO/SAML + SCIM; advanced reporting; Zero Data Retention; team-wide dictionaries |
- **Students:** 70% off Pro and Max with a .edu email, monthly or annual. Pro is $3.60/mo, or $3/mo billed annually; Max is $7.20/mo, or $5.70/mo billed annually.
- **iOS standalone:** $119/yr via the App Store, but a cross-platform Pro subscription already covers iOS.
- **Android:** paid plans are available in the Android app through Google Play, and an existing Aqua subscription covers Android too.
- **Referrals:** share your in-app referral link and the person you invite gets a free month of Aqua; you get a $10 credit when they sign up.
- **What Max adds:** See words live with Realtime Mode, use the Send It voice command, and get early access to new features. Max includes everything in Pro.
- **Aqua Pet:** included on every plan, Free too. Pro adds the Aqua Halo and Max adds the Laser Visor for your pet, and pet leaderboards are for paid plans.
## Developer API
The **Aqua API** creates Aqua dictations and edits, exposes stored dictations, manages transcript customizations and app settings, and provides Avalon batch transcription. The MCP server offers the data and settings operations to AI clients; it does not run dictation.
- Landing page: [aquavoice.com/api](https://aquavoice.com/api)
- Base URL: `https://api.aquavoice.com/v1`
- Authentication: `Authorization: Bearer <api-key>`
- Dictation endpoint: `POST /v1/dictations` ($0.49/audio hour, 10-second minimum)
- API reference: [aquavoice.com/docs/api](https://aquavoice.com/docs/api)
- OpenAPI: [aquavoice.com/docs/api/openapi.yaml](https://aquavoice.com/docs/api/openapi.yaml)
- MCP endpoint: `https://api.aquavoice.com/mcp`
- Transcription endpoint: `POST /v1/audio/transcriptions`
- Model: `avalon-v1.5` (multilingual)
- Pricing: **$0.39 per hour** of audio, billed per second with a 10-second minimum
- Transcription reference: [aquavoice.com/docs/api](https://aquavoice.com/docs/api#tag-transcription)
## Links
- [Try in Browser](https://aquavoice.com/sandbox)
- [Aqua API](https://aquavoice.com/api)
- [Download](https://aquavoice.com/download)
- [Pricing](https://aquavoice.com/pricing)
- [Setup Guide](https://aquavoice.com/guide)
- [Blog](https://aquavoice.com/blog)
- [Changelog](https://aquavoice.com/changelog)
- [Aqua for Mac](https://aquavoice.com/mac)
- [Aqua for Windows](https://aquavoice.com/windows)
- [Realtime Mode](https://aquavoice.com/realtime)
- [Edit Mode](https://aquavoice.com/edit-mode)
- [Deep Context](https://aquavoice.com/deep-context)
- [Aqua Pet](https://aquavoice.com/pet)
- [Use Cases](https://aquavoice.com/use-cases)
- [FAQ](https://aquavoice.com/info/faq)
- [Privacy Policy](https://aquavoice.com/info/privacy)
- [System Status](https://status.aquavoice.com/)
## External Links
- [X / Twitter](https://x.com/aquavoice)
- [Aqua Voice on Y Combinator (W24)](https://www.ycombinator.com/companies/aqua-voice)
- [Hacker News: Launch (2024)](https://news.ycombinator.com/item?id=39828686)
- [Hacker News: Aqua Voice 2 (2025)](https://news.ycombinator.com/item?id=43634005)
- [Product Hunt](https://www.producthunt.com/products/aqua)
## Press & Independent Validation
- [9to5Mac: Aqua vs. Mac Dictation](https://9to5mac.com/2025/08/15/aqua-voice-shows-just-how-good-mac-dictation-could-be-if-apple-just-tried/) (17 Apple errors vs. 1 for Aqua)
- [9to5Mac: Aqua Voice on iPhone](https://9to5mac.com/2026/04/17/aqua-voice-the-best-dictation-app-ive-ever-used-is-now-available-on-iphone/)
- [Open ASR Leaderboard](https://huggingface.co/spaces/hf-audio/open_asr_leaderboard): third-party WER ranking
- Product Hunt: 5.0/5; "Readability Award for AI Dictation Apps, Winter 2025"
## Tech Specs
### Downloads
Always-current installers live at **[aquavoice.com/download](https://aquavoice.com/download)** (auto-updating):
- macOS: Apple Silicon and Intel
- Windows 10/11
- iOS: [App Store](https://apps.apple.com/us/app/aqua-voice-ai-voice-keyboard/id6759074969)
- Android 10 or later: [Google Play](https://play.google.com/store/apps/details?id=com.aquavoice.android)
### Dictation Languages (49)
Arabic, Belarusian, Bengali, Bulgarian, Cantonese, Catalan, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, Galician, German, Greek, Hebrew, Hindi, Hungarian, Indonesian, Irish, Italian, Japanese, Korean, Latvian, Lithuanian, Malay, Maltese, Mandarin, Marathi, Mongolian, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Slovenian, Spanish, Swahili, Swedish, Tamil, Thai, Turkish, Ukrainian, Urdu, Vietnamese, Welsh. Set the language picker to **Auto** to detect automatically.
### Latency
- Startup: under **50ms**
- Instant Mode: text appears ~**450ms** after you stop speaking
- Realtime Mode: words appear in real time as you talk
- Avalon 1.5 is more than **2× faster** than Avalon 1
## Security & Compliance
Aqua Voice has a **SOC 2 Type II audit report** and is **ISO/IEC 27001:2022** certified, and **GDPR** and **HIPAA** compliant.
Aqua Voice received its **SOC 2 Type II audit report** on **March 25, 2026**, demonstrating our commitment to the highest standards of security, availability, and confidentiality. The program was completed with [Vanta](https://www.vanta.com/); [Advantage Partners](https://advantage-partners.com/) was our auditor and [Workstreet](https://www.workstreet.com/) our advisor.
SOC 2 Type II means our security controls were independently audited over an extended observation period, rather than assessed at a single point in time, so teams and enterprises handling sensitive data can use Aqua with confidence. The report is available in our [Trust Center](https://app.vanta.com/aquavoice.com/trust/6f0ehpcbakfh2e73cnoo3r). **Zero Data Retention** is available on Business.
Aqua Voice is also certified against **ISO/IEC 27001:2022** (announced **July 14, 2026**), the international standard for information security management. Certification means an accredited third party examined our Information Security Management System and confirmed the controls are designed and operating effectively. It is the framework security teams outside the United States most often ask for, which makes procurement and onboarding easier for global companies. Same auditor and partners as SOC 2: [Advantage Partners](https://advantage-partners.com/) auditing, [Vanta](https://www.vanta.com/) for evidence automation, [Workstreet](https://www.workstreet.com/) advising. The certificate is downloadable from the Trust Center.
Aqua Voice is also **GDPR and HIPAA compliant** (announced **September 23, 2026**). The GDPR program covers the full life of personal data: a data inventory, privacy risk assessments, agreements with the vendors that process data on our behalf, and documented procedures for requests to access, correct, or delete personal data. The HIPAA program builds on the SOC 2 and ISO 27001 controls: access controls, encryption in transit and at rest, security training, regular risk assessments, and incident response. To use Aqua with protected health information, sign the Business Associate Agreement (BAA) in the app (desktop or web settings). Privacy Mode then turns on and stays on. A team owner or admin can sign for the whole team. The Max and Business plans include the BAA. GDPR and HIPAA are compliance programs, not certifications.
Read more: [Aqua Voice is GDPR and HIPAA compliant](https://aquavoice.com/blog/gdpr-hipaa) · [Aqua Voice is ISO 27001 certified](https://aquavoice.com/blog/iso-27001) · [SOC 2 Type II](https://aquavoice.com/blog/soc2)
### Privacy Mode and what happens to your data
Audio is processed in the cloud and is never sold, and it is never shared for advertising. With **Privacy Mode off** (the default), transcripts may be stored on our servers to improve the product. **Turn Privacy Mode on and they are not stored**; session metadata such as timestamps, device type, and performance metrics may still be collected. **Business** plans can enforce Privacy Mode and Zero Data Retention across an organization. **Deep Context** (screen reading) is a separate setting, off until you enable it. Aqua doesn't keep its screenshots; the words it picks out are stored with the session unless Privacy Mode is on. **Instant Mode** dictation runs on Aqua's own Avalon models; **Realtime Mode** streams audio to a third-party realtime speech provider. The current subprocessor list is in the [Trust Center](https://app.vanta.com/aquavoice.com/trust/6f0ehpcbakfh2e73cnoo3r).
For security inquiries, contact **support@aquavoice.com**.
## Features
### Modes
Aqua has two operation modes:
- **Instant Mode**: Press key → talk → release → see text. Startup <200ms, results ~450ms. The default mode, available on every plan.
- **Realtime Mode**: By default, double-press your Aqua key to go hands-free and see words live in the Aqua toolbar. Press once to finish, or end with "send it" to finish and apply your Send Command setting. Text lands in the app when you finish. Settings also offers **Realtime always** for held-key dictation. Included on **Max** and **Business**, with a preview for free accounts. (Formerly called Streaming Mode; renamed in July 2026.)
Different apps call for different precision. You wouldn't sweat a Cursor prompt the way you would an important email. Instant Mode has the lowest latency and is great for short clips or "chaining" Aqua many times in a row; Realtime Mode gives maximum contextual understanding and precise control over text and formatting. There's no right or wrong way. It's like texting style, some people send many short messages, others one long one.
### Deep Context
Deep Context uses what's on your screen to spell names, terms, and code the way they appear: when you start dictating, Aqua takes one screenshot (nothing is captured between dictations), picks out the words it could mishear, and uses them to recognize what you say. It's optional, off until you turn it on, and works in any app on macOS and Windows, on every plan. Aqua doesn't keep the screenshot; Privacy Mode also redacts the words it picked out. On Business plans, admins can turn it on or off for every member.
Examples from the sandbox engine, with the same recording dictated with and without the screenshot:
```
On screen: Kaitlyn from Lyft moved the demo to Thursday. Can Geoff present?
Aqua w/o Deep Context: Jeff can present. I'll let Kaitlin know.
Aqua w/ Deep Context: Geoff can present. I'll let Kaitlyn know.
On screen: task-list.tsx: const { tasks, filter } = useTaskStore(); useKeyboardShortcuts({ next, previous });
Aqua w/o Deep Context: Add tests for use keyboard shortcuts and use task store.
Aqua w/ Deep Context: Add tests for useKeyboardShortcuts and useTaskStore.
```
It shines when prompting coding agents in Claude Code, Codex, Cursor, and VS Code, and when writing to people whose names are on screen. [About Deep Context](https://aquavoice.com/deep-context)
### Custom Instructions
Tune your output with natural-language rules, similar to ChatGPT custom instructions. For example:
```txt
In iMessage, Slack, & WhatsApp, use all lowercase (gen-z style) except for proper nouns and the pronoun "I".
# PUNCTUATION & SYMBOLS
- When I say "checkbox", insert a Markdown checkbox: - [ ]
# DICTIONARY & MACROS
- My Company: {{My Company Name}} (often misheard as {{common mispronunciation}})
- Our Product: {{Product Name}}
```
### Dictionary
'Impossible' words are no problem. Add names, technical terms (YC W24, factorio, package.json), or custom phrases (Jeffersonian Computing, OPEN-RISOP) and Aqua recognizes them in speech while preserving casing. It's context-aware too: enter "factorio" and Aqua still capitalizes it correctly in "Factorio is a great game."
### Edit Mode
Select any text, in any app, hold your Aqua key, and say the change. Aqua rewrites the selection in place. No mouse, no retyping, no second hotkey to learn. Hold the key with nothing selected and you get normal dictation, exactly as before; hold it with a selection and Aqua switches into Edit Mode automatically.
Live now for every Aqua desktop user on **macOS and Windows** (shipped in v0.17.0), not a separate purchase or tier. Works in native text fields, browsers, Google Docs, chat and email clients, code editors, note apps, and rich-text editors. Wherever you can select text, you can talk to it. No command words needed: say the corrected version of what you selected and Aqua treats it as the replacement. For another revision, select the updated text and say the next change. Desktop Edit Mode does not carry earlier revisions into the next edit, so spoken undo commands such as "undo that," "go back one step," and "go back to the original" are not supported. To reverse an edit, use the host app's own Undo control where supported, or restore the earlier text yourself.
iOS has its own **Voice Edit Mode** for revising your last transcript by voice (see iOS platform notes above); the desktop version is selection-based and works across any app you use.
Read more: [Introducing Edit Mode](https://aquavoice.com/blog/introducing-edit-mode)
### Send It
End a Realtime Mode dictation with "send it" and Aqua strips the command out of your text, ends the session, inserts the message, and applies your **Send Command** setting.
Introduced in desktop **v0.18.0** (July 26, 2026) on **macOS and Windows**. Access follows Realtime Mode: **Max** and **Business** include it, and free accounts can try it within their first 1,000 words. Some older Pro and Team subscriptions retain access. It is not available in Instant Mode or Edit Mode.
By default, Realtime Mode turns on when you go hands-free. Double-press y