Ottex
Mac, iOS
You want dictated emails to follow your saved writing instructions.
You need voice dictation on a Windows computer.
Three tools. Different strengths. Find your fit.
Each tool takes a different approach. Here’s a quick side-by-side to help you choose based on your workflow, platforms, and goals.
Mac, iOS
You want dictated emails to follow your saved writing instructions.
You need voice dictation on a Windows computer.
Mac, Windows, iOS, Android, Web
You want live suggestions during client calls.
You need system-wide dictation for writing across apps.
Mac, Windows, iOS, Android
You want automatically formatted dictation across computers and phones.
You need dictation that works entirely offline.
Hedy costs $12.99/month, Wispr Flow $15/month and Ottex $14/month. Ottex also offers free app access with local models or BYOK (your own API key; provider charges apply).
| Feature | |||
|---|---|---|---|
| Free tier | YesSource: ottex.ai — checked Oct 2026Forever free with local models and BYOK providers. | PartialSource: hedy.ai/pricing — checked Oct 2026Up to 5 hours per month | PartialSource: wisprflow.ai/pricing — checked Oct 20262,000/week on desktop; 1,000/week on mobile; Weekly limit |
| Subscription | $14/moSource: ottex.ai — checked Oct 2026$14/mo — unlimited dictation and meeting intelligence, all hosted models included. | $12.99/moSource: hedy.ai/contact — checked Oct 2026Cloud AI is included, local processing is available, optional external speech providers incur separate API charges, and automatic suggestions stop after 120 minutes per session. | $15/moSource: docs.wisprflow.ai/articles — checked Oct 2026Pro also serves teams at the same per-user prices without a minimum seat requirement; Notetaker access is rolling out gradually. |
| One-time payment | Not applicableSource: ottex.ai — checked Oct 2026Application is free | $299 one-timeSource: hedy.ai/pricing — checked Oct 2026Lifetime feature access and future updates. | NoNo one-time payment plan |
| Bring your own keyPay the model provider, not the middleman | YesSource: ottex.ai — checked Oct 2026OpenRouter, Google AI, OpenAI, Anthropic, Mistral, and compatible providers. | YesSource: hedy.ai/help — checked Oct 2026Deepgram, OpenAI, and xAI speech recognition accept user API keys and bill usage separately from Hedy. | No public claim |
| Education discount | NoSource: ottex.ai — checked Oct 2026Same pricing for everyone. | No public claim | YesSource: docs.wisprflow.ai/articles — checked Oct 2026Eligible students can claim $0/year on desktop or purchase $7.50/month or $72/year, representing 50% off standard Pro; the separate student marketing page advertises three months free followed by $6/month billed annually, which conflicts with the plans documentation. |
For Windows or Android, choose Hedy for meeting coaching or Wispr Flow for dictation; Ottex supports Mac and iOS. Hedy also offers Web access.
| Feature | |||
|---|---|---|---|
| Platforms | Mac, iOSSource: ottex.ai — checked Oct 2026 | Mac, Windows, iOS, Android, WebSource: hedy.ai/downloads — checked Oct 2026 | Mac, Windows, iOS, AndroidSource: docs.wisprflow.ai/articles — checked Oct 2026 |
| Native app footprintLight on memory, instant to invoke | YesSource: ottex.ai — checked Oct 2026Native Swift app, ~50MB RAM. | YesSource: hedy.ai/help — checked Oct 2026The import documentation identifies the installed Mac, Windows, iOS, and Android clients as native apps. | No public claim |
Hedy, Wispr Flow and Ottex capture without bots. Wispr Flow offers desktop chat recording notices; Ottex has an opt-in experimental Mac camera recording watermark; neither mechanism establishes consent.
| Feature | |||
|---|---|---|---|
| Meeting recordingThe call is captured at all | YesSource: ottex.ai — checked Oct 2026With speaker separation. | YesSource: hedy.ai/help — checked Oct 2026Saving session audio requires enabling audio recording, which is off by default. | PartialSource: docs.wisprflow.ai/articles — checked Oct 2026Notetaker records on Mac and Windows, with account rollout, organization, and HIPAA restrictions. |
| Bot-free captureNo "recording bot" joins your call | YesSource: ottex.ai — checked Oct 2026System-audio capture, no bot joins the call. | YesSource: hedy.ai/downloads — checked Oct 2026Meeting capture does not require a bot to join the call. | YesSource: docs.wisprflow.ai/articles — checked Oct 2026Notetaker captures audio from the user's device without joining the call as a 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. | No public claim | No public claim |
| Participant noticesRecording notices in chat or calendar | No public claim | No public claim | PartialSource: docs.wisprflow.ai/articles — checked Oct 2026Mac and Windows can post chat notices in Zoom, Teams, Slack huddles, and foreground Chrome Google Meet; Google Calendar notices require organizer write access, while organization policy can lock chat notices on. |
| Speaker separation | YesSource: ottex.ai — checked Oct 2026 | PartialSource: hedy.ai/help — checked Oct 2026Nemotron separates speakers on supported devices, with names inferred from conversation context or entered manually. | PartialSource: docs.wisprflow.ai/articles — checked Oct 2026Names use calendar details, visible participant tiles, and spoken introductions; unsupported apps, hidden tiles, or shared microphones can retain numbered labels. |
| Calendar detection | YesSource: ottex.ai — checked Oct 2026Calendar-based meeting detection. | PartialSource: hedy.ai/help — checked Oct 2026Mac and Windows detect microphone use by Zoom, Teams, and Webex, with FaceTime detection available on Mac. | YesSource: docs.wisprflow.ai/articles — checked Oct 2026Notetaker detects calls and presents a recording card, with configurable automatic starting. |
| Cross-meeting search | YesSource: ottex.ai — checked Oct 2026 | PartialSource: hedy.ai/help — checked Oct 2026Topic chat searches related sessions; Free includes one topic, while Pro supports unlimited topics and chat across them. | YesSource: docs.wisprflow.ai/articles — checked Oct 2026Ask Wispr in the Notetaker hub searches across meeting notes and cites source meetings. |
| Shared team memory | PartialSource: ottex.ai — checked Oct 2026Public share links, not a full team workspace. | PartialSource: hedy.ai/help — checked Oct 2026Pro users can share Topics containing current and future sessions with recipients who receive read-only access. | PartialSource: docs.wisprflow.ai/articles — checked Oct 2026Shared notes appear in search and Ask Wispr context, subject to sharing permissions and separate transcript-access restrictions. |
Hedy and Wispr Flow can draft follow-ups through external automation or connected AI tools, respectively. Ottex drafts follow-ups, CRM updates and tickets, with structured document templates for transcript information.
| Feature | |||
|---|---|---|---|
| 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. | No public claim | No public claim |
| 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. | YesSource: hedy.ai/help — checked Oct 2026Built-in Quick Prompts send preset questions to session chat, with different prompt sets for each session type. | No public claim |
| Decisions, owners, action itemsLeave the meeting with next steps clear | YesSource: ottex.ai — checked Oct 2026Decisions with owners extracted. | YesSource: hedy.ai/help — checked Oct 2026Session recaps extract action items and next steps into trackable to-do items. | YesSource: docs.wisprflow.ai/articles — checked Oct 2026Generated summaries include a Decisions section with speaker labels. |
| Follow-up email draftedThe outcome is sent, not summarized | YesSource: ottex.ai — checked Oct 2026Drafted from templates or your own. | PartialSource: hedy.ai/integrations — checked Oct 2026A viaSocket template creates an interview follow-up email draft in Gmail from a Hedy session. | PartialSource: wisprflow.ai/notetaker — checked Oct 2026Connected AI tools can draft follow-ups from meeting history through MCP; a dedicated built-in follow-up-email action is unverified. |
| CRM update / ticket draft | YesSource: ottex.ai — checked Oct 2026Structured for the target app. | PartialSource: hedy.ai/integrations — checked Oct 2026A viaSocket workflow sends sales-call notes to a HubSpot contact and requires external automation setup. | No public claim |
| Your rough notes steer the result | YesSource: ottex.ai — checked Oct 2026Rough notes and instructions steer the result. | YesSource: hedy.ai/help — checked Oct 2026Up to 10,000 characters of user-written session notes inform summaries, detailed notes, and chat responses. | PartialSource: docs.wisprflow.ai/articles — checked Oct 2026Ask Wispr reads typed meeting notes as chat context; automatic summaries are stored separately, and note-guided automatic summary generation is unverified. |
Hedy can manually clean session transcripts but lacks system-wide dictation. Wispr Flow and Ottex automatically format dictation; saved writing rules run in Wispr Flow’s desktop beta when enabled and in Ottex profiles.
| Feature | |||
|---|---|---|---|
| Engines | Cloud: Whisper, Gemini 3 Flash, Voxtral. Local: Whisper, Parakeet v3.Source: ottex.ai — checked Oct 2026Hosted routing, BYOK, or fully local. | No public claim | Cloud speech recognition with proprietary post-processingSource: wisprflow.ai/why-flow — checked Oct 2026Wispr describes proprietary models layered over speech recognition and introduced its Canto speech model in September 2026. |
| Local / on-device optionAudio never leaves the machine | YesSource: ottex.ai — checked Oct 2026Whisper and Parakeet v3 run fully on-device. | NoSource: hedy.ai/features — checked Oct 2026Not supported for system-wide dictation. | NoSource: docs.wisprflow.ai/articles — checked Oct 2026Dictation transcription requires an internet connection and runs in the cloud. |
| Model selection per task | YesSource: ottex.ai — checked Oct 2026Choose the model per task and per provider. | NoSource: hedy.ai/features — checked Oct 2026Not supported for system-wide dictation. | No public claim |
| Languages & mixed speechWork that crosses languages mid-sentence | YesSource: ottex.ai — checked Oct 2026100+ languages · Mid-sentence language switching. | NoSource: hedy.ai/features — checked Oct 2026Not supported for system-wide dictation. | PartialSource: docs.wisprflow.ai/articles — checked Oct 2026100+ languages · Mixed Hindi-English speech is supported through explicitly selected Hinglish, and Polish preserves language blends while detection chooses one language per dictation. |
| 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. | NoSource: hedy.ai/features — checked Oct 2026Not supported for system-wide dictation. | YesSource: docs.wisprflow.ai/articles — checked Oct 2026Smart Formatting automatically structures punctuation and lists, with controls on desktop and iOS and formatting always applied on Android. |
| Custom dictionary | YesSource: ottex.ai/docs — checked Oct 2026Add or delete names and specialist terms with preferred spellings; entries provide recognition context during transcription. | NoSource: hedy.ai/features — checked Oct 2026Not supported for system-wide dictation. | YesSource: docs.wisprflow.ai/articles — checked Oct 2026Users can add names, technical terms, and jargon to an editable dictionary and configure recurring spelling replacements. |
| 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. | NoSource: hedy.ai/features — checked Oct 2026Not supported. | YesSource: docs.wisprflow.ai/articles — checked Oct 2026Speaking a saved trigger inserts its stored text during dictation; personal snippets are available on every plan. |
| 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. | NoSource: hedy.ai/features — checked Oct 2026Not supported for system-wide dictation. | PartialSource: docs.wisprflow.ai/articles — checked Oct 2026Desktop beta Auto Apply After Dictation runs a saved custom prompt with optional writing samples before insertion, accepts 1–1,000 words, skips specified cleanup and rapid-repeat cases, and is subject to organization controls. |
| 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. | NoSource: hedy.ai/features — checked Oct 2026Not supported for system-wide dictation. | PartialSource: docs.wisprflow.ai/articles — checked Oct 2026Formal., Casual, very casual, and Excited! presets change capitalization and punctuation with category restrictions and English-only style notices. |
| 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. | PartialSource: hedy.ai/help — checked Oct 2026Completed session transcripts can be manually cleaned and translated using cloud AI on the original capturing device. | PartialSource: docs.wisprflow.ai/articles — checked Oct 2026Desktop beta Transforms rewrite selected or readable field text with built-in or saved prompts at 1–1,000 words; iOS Polish accepts 10–1,000 words with different controls. |
| Per-app output rules | YesSource: ottex.ai — checked Oct 2026Per-app output rules: exact in AI chats, polished in email. | NoSource: hedy.ai/features — checked Oct 2026Not supported. | PartialSource: docs.wisprflow.ai/articles — checked Oct 2026Styles are selected for app categories, with web-app detection on desktop; some iOS layouts apply one default style everywhere. |
Choose Hedy for live meeting coaching or Wispr Flow for formatted dictation across computers and phones. Choose Ottex for dictation with saved writing rules or local processing on Mac, provided you do not need Windows or Android.
Hedy includes up to 5 meeting hours/month; Wispr Flow’s 2,000 desktop or 1,000 mobile words/week cover only about 15 or 8 minutes of speech. Ottex offers free app access with local models or your own API key, with provider charges for BYOK.
Hedy Pro costs $12.99/month or $99.99/year, with a $299 lifetime license; Wispr Flow Pro costs $15/month or $144/year, with another annual-plan listing at $143.99. Ottex Pro costs $14/month or $168/year; local-model and BYOK app access are free, with provider charges for BYOK.
Ottex is the choice for on-device dictation transcription; Wispr Flow processes dictation in the cloud. Hedy uses cloud AI for transcript cleanup and translation, but its audio-processing location is unspecified, preventing a reliable comparison of its meeting-audio privacy.
Switch to Wispr Flow for dictation into other apps with automatic formatting, a custom dictionary and voice snippets; stay with Hedy for live meeting coaching. Ottex supports those dictation features and saved writing rules, but runs on Mac and iOS.
Hedy and Wispr Flow support Windows and Android; Hedy also has Web access. Ottex supports Mac and iOS, so choose Wispr Flow for Windows or Android dictation and Hedy for meeting coaching on those platforms.
Wispr Flow requires internet for dictation, and Hedy has no verified offline processing option. Ottex can transcribe dictation entirely on-device with Whisper or Parakeet v3; cloud or BYOK processing is a separate choice.