Last updated: November 18, 2026

Aqua Voice vs Spokenly

Spokenly lets you choose your speech model and has a generous free tier. Aqua Voice is a managed app on its own model, Avalon, built for technical words.

Get Started on Mac

Aqua Voice vs Spokenly, side by side.

FeatureAqua VoiceSpokenly
Speech modelAvalon (own, purpose-trained)Local models, BYOK, or managed Pro cloud
Pro, monthly billing$12/month$15/month
Pro, annual billing$120/year ($10/month)$144/year ($12/month)
Free tier2,000 lifetime wordsLocal models, no limits + free BYOK
Voice Arena dictation benchmark#1 of 14, 80.5% with no edits#6 of 14, 73.8% with no edits
Technical-term accuracy97.4% (AISpeak-10, our benchmark)Not published (model + hardware)
SetupInstall app; no local model downloadManaged Pro, or choose local/BYOK
Processing & securityCloud; SOC 2 Type II audit report, ISO 27001, GDPR, HIPAAOn-device, BYOK, or managed cloud
Works offlinecloudlocal models
Mac / Windows / iPhone / AndroidYesYes
LinuxNoYes
Bring your own model / keyAvalon API insteadYes
Languages49100+
Real-time + screen contextDeep Context; Realtime Mode on MaxReal-time streaming on Pro
MCP supportYesYes
Meeting notesMac, Windows, iPhone, AndroidRecording only, no notes
Point at your screen while you talkAqua PenNo
Desktop petAqua PetNo
Best forAccuracy, zero setup, lower price, technical/AI usersModel choice, big free tier, BYOK, more languages

Where each one wins.

Where Aqua Voice is better

  • More accurate in an independent test

    Voice Arena played the same recordings into 14 dictation apps on a Mac. Aqua Voice ranked #1 and Spokenly ranked #6: 80.5% of Aqua Voice's drafts were perfect, ready to send without a single change, against 73.8% for Spokenly.

  • Zero setup, always current

    Aqua runs one managed model, so there is nothing to choose and no API key to set up. Spokenly Pro is also managed; its free modes give more control.

  • Screen-context awareness

    On a computer, Aqua reads the active window and formats for where you type: code-aware in your editor, casual in Messages. Aqua also takes meeting notes.

  • A lower price for managed cloud

    Aqua Pro is $10 a month billed annually, or $12 monthly. Spokenly Pro, its managed cloud plan, is $12 a month billed annually, or $15 monthly.

Where Spokenly wins

  • Generous free tier

    Local models have no word limit, and you can bring your own cloud key for free. Aqua's free tier is 2,000 lifetime words.

  • Model choice and BYOK

    Pick local Whisper or Parakeet, or your own cloud provider with an API key. Local models also work offline.

  • Linux and more languages

    Spokenly runs on Linux and advertises 100+ languages. Aqua Voice covers 49.

80.5%Aqua Voice
73.8%Spokenly

Perfect drafts, ready to send without a single change, on Voice Arena’s independent dictation benchmark, run on a Mac in US English.Read the resultsVoice Arena

What models does Spokenly use?

Spokenly can run Whisper or NVIDIA's Parakeet locally, a cloud provider through your own key, or managed cloud models with Pro. We measured Avalon against Whisper Large v3, one of the open models you can run in Spokenly.

Voice Arena, an independent benchmark, tested both apps on the same recordings. 80.5% of Aqua Voice's drafts were perfect, ready to send without a single change, against 73.8% for Spokenly.

Bring-your-own-model vs one managed model

Spokenly (spokenly.app) is an indie dictation app built around choice. It does not ship its own model. You run open models on your machine, connect your own cloud provider with an API key, or pay for managed cloud with Pro.

Aqua Voice runs its own model, Avalon, in the cloud, so there is nothing to choose or configure, and the model keeps improving. The trade-off is one managed model instead of a front-end for any model.

Frequently asked questions.

Is Aqua Voice a good Spokenly alternative?

It depends on what you value. Spokenly is an indie app that runs a choice of models (local Whisper/Parakeet or your own cloud keys) with a generous free tier. Aqua Voice is a managed service on its own model, Avalon, with published technical-term results (97.4% on AISpeak-10), zero setup, screen-context awareness, and ongoing improvements. If you want flexible model choice and a big free tier, Spokenly is great; if you want one polished product with managed dictation with published model results and nothing to configure, Aqua Voice is the stronger choice.

What's the difference between Aqua Voice and Spokenly?

They take different approaches to the model. Spokenly is a flexible front-end that lets you pick a model: open speech models like OpenAI's Whisper or NVIDIA's Parakeet running locally, a cloud provider through your own API key, or managed cloud models with Pro. Aqua Voice is a managed cloud app running Avalon, its own purpose-trained model, with screen-context awareness and Realtime Mode on Max. Both run on Mac, Windows, iPhone, and Android and dictate into any app with a hotkey.

Is Aqua Voice more accurate than Spokenly?

In Voice Arena's test, yes. Voice Arena, an independent benchmark, played the same recordings into 14 dictation apps on a Mac and counted the perfect drafts, the ones a person could send without a single change. Aqua Voice ranked #1 with 80.5%, and Spokenly ranked #6 with 73.8%. Spokenly's accuracy changes with the model you choose.

Is Aqua Voice cheaper than Spokenly?

Yes, for the managed cloud plans. Aqua Pro is $120 a year, or $12 month to month. Spokenly Pro is $144 a year, or $15 month to month. Spokenly also offers unlimited free local models, free BYOK (provider charges apply), and Local+ for $29 once; Aqua's free plan includes 2,000 lifetime words.

Does Aqua Voice run on the same platforms as Spokenly?

Both support Mac, Windows, iPhone, and Android. Spokenly also supports Linux, which Aqua Voice does not.

Does Aqua Voice work offline like Spokenly's local models?

No. Spokenly can run Whisper or Parakeet on-device, so those local models work offline and keep your audio on your machine. Aqua Voice processes audio in the cloud to run the Avalon model, so it needs an internet connection. If fully offline, on-device dictation is a requirement, Spokenly's local mode is the better fit.

Does Aqua Voice let me bring my own model or API key?

Not in the way Spokenly does. Spokenly is built around model choice: you can run local Whisper/Parakeet or plug in your own cloud provider key. Aqua Voice runs one model, Avalon, that we train and host, so there's nothing to choose or configure. For developers who want Avalon-grade accuracy in their own tools, we offer the Avalon API (OpenAI-compatible, $0.39/hour). Aqua also supports MCP for sessions, customizations, and settings.

Is Aqua Voice good for coding and AI prompting?

Yes, it's what Aqua Voice is built for. Avalon was trained on the speech developers and AI users produce, reaching 97.4% accuracy on technical terms like programming keywords, framework names, and CLI commands. It also reads the active app for context and offers the Avalon API for developers. With Spokenly, technical accuracy comes down to which model you choose and how you've set it up.

Compare Aqua with

See All Comparisons