Keep voice typing. Change what holds you back.

FluidVoice is the clearest zero-cost replacement: local dictation is unlimited, with no trial or paid tier. VoiceInk offers a $25 one-time Mac license, and building it from source is free. Ottex offers free app access through both local models and your own API key, with provider usage charges separate; its $14/month Pro plan is a flat subscription. A one-time app license and cloud usage charges are separate costs, so choose local processing when eliminating both is the priority.

See the evidence — 28 claims across 6 toolsverified Oct 2026Show tableHide table

	Ottex	Aqua Voice	Spokenly	FluidVoice	VoiceInk	Granola
Free tier	YesSource: ottex.ai — checked Oct 2026Forever free with local models and BYOK providers.	PartialSource: aquavoice.com/vs — checked Oct 20261,000 free words	PartialSource: spokenly.app/pricing — checked Oct 2026No usage limits	PartialSource: fluidvoice.org/download — checked Oct 2026no trial, word limit or paid tier	YesSource: github.com/Beingpax — checked Oct 2026The Mac app can be built free from source; no usage allowance is published, automatic updates are excluded, and cloud API usage costs extra.	PartialSource: docs.granola.ai/help-center — checked Oct 2026No daily limit; Last 30 days only in the app
Subscription	$14/moSource: ottex.ai — checked Oct 2026$14/mo — unlimited dictation and meeting intelligence, all hosted models included.	$10/moSource: aquavoice.com/pricing — checked Oct 2026Includes Custom Instructions and an expanded dictionary.	$6.99/moSource: spokenly.app/team — checked Oct 2026Each seat includes full Pro with a permanent 30% discount and centralized billing.	NoNo subscription plan	NoNo subscription plan	$14/moSource: docs.granola.ai/help-center — checked Oct 2026Pricing is per active workspace member, with monthly billing only.
One-time payment	Not applicableSource: ottex.ai — checked Oct 2026Application is free	NoNo one-time payment plan	Not applicableSource: spokenly.app/pricing — checked Oct 2026Application is free	Not applicableSource: fluidvoice.org/download — checked Oct 2026Application is free	$25 one-timeSource: tryvoiceink.com/buy — checked Oct 2026Lifetime updates	Not applicableSource: docs.granola.ai/help-center — checked Oct 2026Application is free
Bring your own keyPay the model provider, not the middleman	YesSource: ottex.ai — checked Oct 2026OpenRouter, Google AI, OpenAI, Anthropic, Mistral, and compatible providers.	No public claim	YesSource: spokenly.app/privacy — checked Oct 2026BYOK audio and text travel directly from the device to the selected provider.	YesSource: fluidvoice.org/docs — checked Oct 2026Optional cloud cleanup uses the user's API key and separately billed provider account.	YesSource: tryvoiceink.com/docs — checked Oct 2026Cloud transcription and enhancement providers connect through user-supplied API keys, with provider charges excluded from the license.	NoSource: docs.granola.ai/help-center — checked Oct 2026Granola does not support bringing your own AI models.
Education discount	NoSource: ottex.ai — checked Oct 2026Same pricing for everyone.	YesSource: aquavoice.com/pricing — checked Oct 2026Students with eligible school emails receive 70% off: Pro costs $3/month monthly or $2.40/month billed annually, and Max costs $9/month monthly or $7.20/month billed annually; accepted domains include .edu, .ac.uk, .ac.jp, .ac.kr, and .ac.in.	YesSource: spokenly.app/students — checked Oct 2026Verified students receive 50% off Pro at $4.99/month or $49.99/year after signing in with an academic email and emailing a student ID to support.	No public claim	YesSource: tryvoiceink.com/faq — checked Oct 2026Students can request a discount with a student ID; discounted prices, percentage, and billing terms are not published.	YesSource: granola.ai/students — checked Oct 2026Accepted currently enrolled students at accredited universities in the US, UK, and Canada receive Business for $0 for 12 months; no percentage discount or recurring monthly or annual student price is published.

Aqua Voice already covers Mac, Windows 10 and 11, and iPhone; Android remains waitlist-only, and its Linux CLI handles configuration and audio files rather than establishing desktop dictation support. Wispr Flow is the stronger choice for a shipping Android app alongside Windows, Mac and iOS. Ottex covers Mac and iOS only. Aqua Voice's application framework is unspecified, so there is no supported basis for claiming a native-versus-Electron quality advantage.

See the evidence — 11 claims across 6 toolsverified Oct 2026Show tableHide table

	Ottex	Aqua Voice	Spokenly	FluidVoice	VoiceInk	Granola
Platforms	Mac, iOSSource: ottex.ai — checked Oct 2026	Mac, Windows, iOSSource: aquavoice.com/guide — checked Oct 2026Some platforms in beta/waitlist	Mac, Windows, iOS, LinuxSource: spokenly.app/download — checked Oct 2026Some platforms in beta/waitlist	MacSource: fluidvoice.org/download — checked Oct 2026Some platforms in beta/waitlist	MacSource: tryvoiceink.com/docs — checked Oct 2026	Mac, Windows, iOS, AndroidSource: docs.granola.ai/help-center — checked Oct 2026
Native app footprintLight on memory, instant to invoke	YesSource: ottex.ai — checked Oct 2026Native Swift app, ~50MB RAM.	No public claim	YesSource: spokenly.app/android — checked Oct 2026The macOS and iOS applications are built with Swift.	PartialSource: raw.githubusercontent.com/altic-dev — checked Oct 2026The macOS application uses SwiftUI and AppKit; the Windows implementation was not verified.	YesSource: github.com/beingpax — checked Oct 2026The Mac application is native.	NoSource: granola.ai/jobs — checked Oct 2026The desktop application uses Electron with OS integrations; mobile implementation frameworks remain unverified.

Aqua Voice has no meeting recording, so this switch adds a job it cannot perform. Ottex captures system audio without a bot and separates speakers, but its public share links are not a full shared team workspace. Granola offers shared meeting-note collections and bot-free transcription, but retains no playable audio or video recordings. Ottex's experimental macOS camera recording watermark requires setup and does not establish consent; participant chat/calendar recording notices remain unconfirmed.

See the evidence — 40 claims across 6 toolsverified Oct 2026Show tableHide table

	Ottex	Aqua Voice	Spokenly	FluidVoice	VoiceInk	Granola
Meeting recordingThe call is captured at all	YesSource: ottex.ai — checked Oct 2026With speaker separation.	NoSource: aquavoice.com/creators — checked Oct 2026Not supported.	PartialSource: spokenly.app/dictation-for-mac — checked Oct 2026Meeting recording ships on Mac and requires macOS 14.4 or later.	PartialSource: github.com/altic-dev — checked Oct 2026FluidMeet records meetings locally in macOS v1.6.10-beta.7.	NoSource: tryvoiceink.com/best-typeless-alternatives — checked Oct 2026Not supported.	PartialSource: docs.granola.ai/help-center — checked Oct 2026Live audio is captured for transcription, but playable audio and video recordings are not retained.
Bot-free captureNo "recording bot" joins your call	YesSource: ottex.ai — checked Oct 2026System-audio capture, no bot joins the call.	NoSource: aquavoice.com/creators — checked Oct 2026Not supported.	YesSource: spokenly.app/blog — checked Oct 2026Mac meeting recording captures audio without a bot joining the call.	PartialSource: raw.githubusercontent.com/altic-dev — checked Oct 2026The macOS beta captures meeting-application audio and microphone audio directly on the computer.	NoSource: tryvoiceink.com/best-typeless-alternatives — checked Oct 2026Not supported.	YesSource: granola.ai/security — checked Oct 2026The app captures device audio without adding a participant bot.
Camera recording watermarkShow recording in your camera video	PartialExperimental macOS virtual camera adds an Ottex icon to video; install/enable the extension, select it and turn video on. Guide covers Meet in Chrome and Zoom desktop; effects may obscure it.	NoSource: aquavoice.com/creators — checked Oct 2026Not supported.	No public claim	No public claim	NoSource: tryvoiceink.com/best-typeless-alternatives — checked Oct 2026Not supported.	PartialSource: docs.granola.ai/help-center — checked Oct 2026All plans can install and select a virtual camera on macOS 14+ or Windows 11; Enterprise enforcement requires chat notices and may require workspace activation by support.
Participant noticesRecording notices in chat or calendar	No public claim	NoSource: aquavoice.com/creators — checked Oct 2026Not supported.	No public claim	No public claim	NoSource: tryvoiceink.com/best-typeless-alternatives — checked Oct 2026Not supported.	PartialSource: docs.granola.ai/help-center — checked Oct 2026Desktop chat notices support Meet through a Chromium extension and Zoom or Teams through app setup; Enterprise admins can enforce them, while calendar-invite notices remain unverified.
Speaker separation	YesSource: ottex.ai — checked Oct 2026	NoSource: aquavoice.com/creators — checked Oct 2026Not supported.	PartialSource: spokenly.app/blog — checked Oct 2026Saved meeting recordings can be transcribed with voice-based speaker labels that may require manual correction.	PartialSource: github.com/altic-dev — checked Oct 2026FluidMeet includes speaker labels in the macOS beta; automatic identification of participants by real name is unverified.	NoSource: tryvoiceink.com/best-typeless-alternatives — checked Oct 2026Not supported.	PartialSource: docs.granola.ai/help-center — checked Oct 2026Configured desktop speaker tags identify participants in Meet, Zoom, and Teams; mobile transcripts use speaker labels.
Calendar detection	YesSource: ottex.ai — checked Oct 2026Calendar-based meeting detection.	NoSource: aquavoice.com/creators — checked Oct 2026Not supported.	PartialSource: spokenly.app/releases — checked Oct 2026Mac meeting detection is documented in release notes, including Safari support.	PartialSource: raw.githubusercontent.com/altic-dev — checked Oct 2026The macOS beta optionally detects Zoom, Teams, Webex, and supported browser meetings, then offers user-started recording.	NoSource: tryvoiceink.com/best-typeless-alternatives — checked Oct 2026Not supported.	YesSource: docs.granola.ai/help-center — checked Oct 2026Calendar reminders and microphone-use detection prompt the user to start notes.
Cross-meeting search	YesSource: ottex.ai — checked Oct 2026	NoSource: aquavoice.com/creators — checked Oct 2026Not supported.	No public claim	PartialSource: github.com/altic-dev — checked Oct 2026The macOS beta's Global Search includes transcripts across the application.	NoSource: tryvoiceink.com/best-typeless-alternatives — checked Oct 2026Not supported.	YesSource: docs.granola.ai/help-center — checked Oct 2026Chat queries multiple meetings, with Basic limited to the accessible 30-day history.
Shared team memory	PartialSource: ottex.ai — checked Oct 2026Public share links, not a full team workspace.	NoSource: aquavoice.com/creators — checked Oct 2026Not supported.	No public claim	No public claim	NoSource: tryvoiceink.com/best-typeless-alternatives — checked Oct 2026Not supported.	YesSource: docs.granola.ai/help-center — checked Oct 2026Folder-level Chat queries shared meeting-note collections.

Ottex is the stronger fit when a meeting must become follow-up email, structured CRM-update or ticket drafts. Its meeting template library extracts transcript information into documents such as client-call reports, while its separate transcript chat prompt library supplies reusable questions and analysis prompts. Granola combines transcripts, typed notes and calendar context into enhanced notes, with desktop meeting-type templates and a separate Recipes prompt library. Its automatic follow-up emails require a paid plan or trial, connected Gmail, an external guest and no more than 10 attendees; CRM note synchronization does not establish structured CRM-update drafting.

See the evidence — 25 claims across 6 toolsverified Oct 2026Show tableHide table

	Ottex	Aqua Voice	Spokenly	FluidVoice	VoiceInk	Granola
Meeting template libraryTurn a transcript into a structured document	YesSource: ottex.ai — checked Oct 2026Choose a ready-made document template to extract relevant information from a meeting transcript into a structured document, such as a product review or client-call report.	NoSource: aquavoice.com/creators — checked Oct 2026Meeting-transcript document templates are not supported.	No public claim	No public claim	NoSource: tryvoiceink.com/best-typeless-alternatives — checked Oct 2026Ready-made documents that extract and structure recorded meeting transcripts are not supported.	PartialSource: docs.granola.ai/help-center — checked Oct 2026Desktop users select built-in meeting-type templates that generate or regenerate enhanced notes in the chosen structure.
Transcript chat prompt libraryReady-made prompts for AI chat about meetings	YesSource: ottex.ai — checked Oct 2026Use ready-made reusable prompts in AI chat to ask questions, analyze discussions and extract information from meeting transcripts.	NoSource: aquavoice.com/creators — checked Oct 2026Reusable prompts for chat over meeting transcripts are not supported.	No public claim	No public claim	NoSource: tryvoiceink.com/best-typeless-alternatives — checked Oct 2026A reusable prompt library for AI chat over recorded meeting transcripts is not supported.	YesSource: docs.granola.ai/help-center — checked Oct 2026The Recipes menu and Discover tab provide reusable Granola and community prompts that run over individual or multiple meetings.
Decisions, owners, action itemsLeave the meeting with next steps clear	YesSource: ottex.ai — checked Oct 2026Decisions with owners extracted.	NoSource: aquavoice.com/creators — checked Oct 2026Not supported.	No public claim	PartialSource: raw.githubusercontent.com/altic-dev — checked Oct 2026The macOS beta offers a Key decisions output, while assignment of decision owners is unverified.	NoSource: tryvoiceink.com/best-typeless-alternatives — checked Oct 2026Not supported.	YesSource: docs.granola.ai/help-center — checked Oct 2026Chat extracts action items from meeting notes and transcripts.
Follow-up email draftedThe outcome is sent, not summarized	YesSource: ottex.ai — checked Oct 2026Drafted from templates or your own.	NoSource: aquavoice.com/creators — checked Oct 2026Not supported.	No public claim	No public claim	NoSource: tryvoiceink.com/best-typeless-alternatives — checked Oct 2026Not supported.	PartialSource: docs.granola.ai/help-center — checked Oct 2026Automatic drafts require a paid plan or trial, connected Gmail, an external guest, and no more than 10 attendees.
CRM update / ticket draft	YesSource: ottex.ai — checked Oct 2026Structured for the target app.	NoSource: aquavoice.com/creators — checked Oct 2026Not supported.	No public claim	No public claim	NoSource: tryvoiceink.com/best-typeless-alternatives — checked Oct 2026Not supported.	No public claim
Your rough notes steer the result	YesSource: ottex.ai — checked Oct 2026Rough notes and instructions steer the result.	NoSource: aquavoice.com/creators — checked Oct 2026Not supported.	NoSource: spokenly.app/comparison — checked Oct 2026Not supported.	No public claim	NoSource: tryvoiceink.com/best-typeless-alternatives — checked Oct 2026Not supported.	YesSource: docs.granola.ai/help-center — checked Oct 2026Typed raw notes guide generated notes alongside the transcript and calendar context.

Aqua Voice already applies saved writing instructions, so that feature alone is not a reason to switch. Ottex adds verified on-device Whisper and Parakeet v3 recognition, per-app output rules and mid-sentence language switching across a listed 100 languages, compared with Aqua Voice's 50. Spokenly also lists 100 languages and offers unlimited free local models with a Local Only Mode that blocks outbound network access; its documented mixed-language switching depends on Gemini 3.5 Transcribe. Aqua Voice's iOS offline downloads do not yet establish a fully local audio-to-final-text workflow.

See the evidence — 59 claims across 6 toolsverified Oct 2026Show tableHide table

	Ottex	Aqua Voice	Spokenly	FluidVoice	VoiceInk	Granola
Engines	Cloud: Whisper, Gemini 3 Flash, Voxtral. Local: Whisper, Parakeet v3.Source: ottex.ai — checked Oct 2026Hosted routing, BYOK, or fully local.	Avalon 1.5, WhisperSource: aquavoice.com/info — checked Oct 2026Desktop model choices vary by app version and account access.	Whisper, NVIDIA Parakeet, Apple Speech Analyzer, OpenAI GPT-4o Transcribe, Deepgram Nova, SonioxSource: spokenly.app/docs — checked Oct 2026Local and cloud transcription engines are selectable per mode.	Nemotron Speech 3.5, Nemotron 3.5 Multilingual, Parakeet Flash Beta, Parakeet TDT v3, Parakeet TDT v2, Cohere Transcribe, Apple Speech, WhisperSource: fluidvoice.org/models — checked Oct 2026The macOS model lineup varies by hardware and operating-system compatibility.	Parakeet, Nemotron, Whisper, Cohere Transcribe, SenseVoice, Apple Speech, BYOK cloud providersSource: tryvoiceink.com/docs — checked Oct 2026Transcription models and optional text-enhancement models are selected separately.	No public claim
Local / on-device optionAudio never leaves the machine	YesSource: ottex.ai — checked Oct 2026Whisper and Parakeet v3 run fully on-device.	PartialSource: aquavoice.com/changelog — checked Oct 2026The iOS changelog documents downloadable offline models, but supported models and modes remain unspecified.	YesSource: spokenly.app/docs — checked Oct 2026Downloaded local models transcribe offline, and Local Only Mode blocks outbound network access.	YesSource: fluidvoice.org — checked Oct 2026Local recognition and local cleanup work offline after their required assets are installed.	YesSource: tryvoiceink.com/docs — checked Oct 2026Downloaded local transcription models run on the Mac, with Apple Silicon recommended and Intel reliability caveats.	NoSource: docs.granola.ai/help-center — checked Oct 2026System-wide dictation is not supported.
Model selection per task	YesSource: ottex.ai — checked Oct 2026Choose the model per task and per provider.	PartialSource: aquavoice.com/info — checked Oct 2026The desktop Transcription Model selector exposes models available to the account.	YesSource: spokenly.app/docs — checked Oct 2026Users choose transcription models and AI providers per mode.	YesSource: fluidvoice.org/models — checked Oct 2026Users can download and switch speech models in the application.	YesSource: tryvoiceink.com/docs — checked Oct 2026Each Mode selects its transcription model and optional enhancement provider and model.	NoSource: docs.granola.ai/help-center — checked Oct 2026System-wide dictation is not supported.
Languages & mixed speechWork that crosses languages mid-sentence	YesSource: ottex.ai — checked Oct 2026100+ languages · Mid-sentence language switching.	No public claim	PartialSource: spokenly.app/blog — checked Oct 2026100+ languages · Gemini 3.5 Transcribe supports switching languages mid-sentence.	PartialSource: fluidvoice.org/docs — checked Oct 202699+ languages · Mid-sentence language switching can produce errors and requires testing with the selected model.	No public claim	NoSource: docs.granola.ai/help-center — checked Oct 2026System-wide dictation is not supported.
Automatic formatting	YesSource: ottex.ai/docs — checked Oct 2026Dictation automatically fixes punctuation, groups ideas into paragraphs and formats enumerations as lists. Formatting toggles and profile rules customize output.	YesSource: aquavoice.com/changelog — checked Oct 2026Dictation automatically adds punctuation and paragraph breaks, with additional formatting configurable through Custom Instructions.	PartialSource: spokenly.app/docs — checked Oct 2026Models add punctuation, and optional Smart Paragraphs on Mac adds paragraph breaks; automatic list formatting remains unverified.	PartialSource: raw.githubusercontent.com/altic-dev — checked Oct 2026Optional AI cleanup fixes punctuation and capitalization, while spoken directives create line breaks and list items.	YesSource: tryvoiceink.com/features — checked Oct 2026Modes offer configurable paragraph breaks, while optional AI enhancement can produce punctuated paragraphs and lists.	NoSource: docs.granola.ai/help-center — checked Oct 2026System-wide dictation is not supported.
Custom dictionary	YesSource: ottex.ai/docs — checked Oct 2026Add or delete names and specialist terms with preferred spellings; entries provide recognition context during transcription.	YesSource: aquavoice.com/guide — checked Oct 2026Users can add and remove names, specialist terms, and acronyms in Dictionary.	PartialSource: spokenly.app/docs — checked Oct 2026Supported models accept custom keyterms; ElevenLabs live transcription applies only the first 50 terms.	YesSource: fluidvoice.org/features — checked Oct 2026Custom Dictionary accepts preferred spellings for names and jargon, with JSON import and export.	PartialSource: tryvoiceink.com/docs — checked Oct 2026Editable Vocabulary entries guide supported transcription models and AI enhancement, with support dependent on the selected model.	NoSource: docs.granola.ai/help-center — checked Oct 2026System-wide dictation is not supported.
Voice snippetsSay a saved phrase to insert a link or text	YesSource: ottex.ai/docs — checked Oct 2026Save a voice trigger and expansion text; saying the trigger while dictating inserts the saved URL or text in place.	YesSource: aquavoice.com/guide — checked Oct 2026Replacements expand spoken phrases into saved text such as calendar links and email addresses.	NoSource: spokenly.app/comparison — checked Oct 2026Not supported.	No public claim	YesSource: tryvoiceink.com/docs — checked Oct 2026Word Replacements expand spoken phrases into saved URLs, addresses, signatures, or other text after dictation.	NoSource: docs.granola.ai/help-center — checked Oct 2026System-wide dictation is not supported.
Custom voice instructionsFree-form rules applied after dictation	YesSource: ottex.ai — checked Oct 2026Saved profile instructions automatically process dictation before insertion; rules can include writing examples, personal phrasing and email signatures.	PartialSource: aquavoice.com/guide — checked Oct 2026Plans with Custom Instructions automatically apply saved writing rules and examples to dictation, including email signatures.	YesSource: spokenly.app/docs — checked Oct 2026Saved mode AI Instructions process each dictation before its configured auto-insert action using the selected AI provider.	YesSource: fluidvoice.org/docs — checked Oct 2026Saved user-written prompts automatically process dictation before insertion when AI cleanup is enabled.	PartialSource: tryvoiceink.com/docs — checked Oct 2026Saved custom prompts automatically process dictation before Paste delivery in compatible enhanced Modes; Refine excludes custom prompts and short dictations can skip enhancement.	NoSource: docs.granola.ai/help-center — checked Oct 2026System-wide dictation is not supported.
Tone presetsChoose a predefined writing style	YesSelect built-in Messaging or Email profiles for casual or professional dictation; assigning apps or websites enables automatic profile activation.	PartialSource: aquavoice.com/changelog — checked Oct 2026Casual Messaging is a selectable lowercase style for messaging apps; a broader preset selector is unverified.	No public claim	No public claim	PartialSource: tryvoiceink.com/docs — checked Oct 2026Built-in Default, Chat, and Email prompts provide selectable writing styles through compatible AI-enhanced Modes.	NoSource: docs.granola.ai/help-center — checked Oct 2026System-wide dictation is not supported.
Text transforms / AI ShortcutsApply an AI action to existing text	YesSource: ottex.ai/docs — checked Oct 2026Select or copy existing text, open Omnibar and run an AI Shortcut to rewrite, translate, summarize or apply a custom prompt; the result is copied/pasted.	YesSource: aquavoice.com/edit-mode — checked Oct 2026Edit Mode rewrites selected text by voice on desktop, excluding search fields, address bars, and selections over 6,000 characters.	No public claim	PartialSource: fluidvoice.org/features — checked Oct 2026Write Mode replaces selected text using spoken rewrite instructions in Accessibility-compatible fields, with AI-provider compatibility restrictions.	YesSource: tryvoiceink.com/docs — checked Oct 2026A compatible AI-enhanced Mode rewrites selected or clipboard text using saved prompts and spoken instructions, then pastes the result.	PartialSource: docs.granola.ai/help-center — checked Oct 2026Desktop Chat rewrites, expands, corrects, or translates selected sections of Granola meeting notes.
Per-app output rules	YesSource: ottex.ai — checked Oct 2026Per-app output rules: exact in AI chats, polished in email.	PartialSource: aquavoice.com/changelog — checked Oct 2026Casual Messaging enforces lowercase in apps such as Slack, iMessage, and Discord.	PartialSource: spokenly.app/docs — checked Oct 2026Mac modes automatically activate for configured applications or websites.	YesSource: fluidvoice.org/docs — checked Oct 2026User-authored per-app instructions are selected automatically for the focused application.	YesSource: tryvoiceink.com/docs — checked Oct 2026App and supported-browser website triggers automatically select Modes with different processing and output settings.	NoSource: docs.granola.ai/help-center — checked Oct 2026System-wide dictation is not supported.