Amical

AI Dictation for Deep Work

Draft the chapter, the paper, the long essay in flow instead of fighting the keyboard. Voice is the lower-friction medium when the thinking has to run for an hour straight.

Download

Why typing is slowing deep work down

Typing breaks the flow state

A long focused writing session needs the input speed to match the thinking pace, otherwise the editor brain wakes up between sentences and the flow collapses. Typing forces enough micro-pauses that an hour of writing produces forty minutes of actual thinking.

Hand fatigue caps the session length

After two hours of intense typing the wrists, the shoulders, and the small muscles in the hands all start to push back. The session ends earlier than it could have, and consecutive deep-work days are physically harder to sustain than the brain alone would otherwise need them to be.

Draft pace lags the thinking pace

A clear argument forms in the head in fifteen seconds but takes ninety seconds to type. By the time the first sentence is on the page the next two have evaporated, and the draft always feels thinner than the thinking that actually happened behind it.

A day with Amical

  1. Morning deep-work block

    Two-hour block on the calendar, do-not-disturb on, coffee in hand. Open the draft, speak through the next section at thinking pace, watch a thousand words land in the time it would have taken to type four hundred.

  2. Mid-session pivot

    Midway through the block a sharper argument structure emerges. Pause, speak a quick outline of the new shape into a margin note, then dictate the rewritten section straight into the draft — far cheaper than the same pivot would have been by keyboard.

  3. Long afternoon session

    A second two-hour block in the afternoon would have been physically rough on hands and wrists after the morning. With voice the second block is as productive as the first because the input surface is not the bottleneck, and consecutive deep-work days actually compound.

  4. End-of-day light edit

    Read through the day's draft with the keyboard for fifteen minutes — fix the few transcription typos, tighten phrasing, mark the open threads to pick up tomorrow. The session ends with substantially more usable draft on the page than a typed equivalent would have produced.

What Amical does for deep work

Sustained flow for an hour straight

Voice keeps the input speed close to the thinking speed, which is the single condition flow state actually needs to sustain across a long writing session. Most users find the average usable session length grows from forty minutes of effective work in an hour of typing to roughly fifty-five minutes of effective work in an hour of dictation.

Lower friction for long-form output

A typed five-thousand-word draft is a meaningful keystroke load on top of the thinking work itself, and the load compounds across consecutive deep-work days. Voice cuts the physical input cost to roughly nothing, which is what makes book-length and paper-length writing schedules sustainable across weeks rather than just inside a single burst.

On-device private model for drafts

Long-form work — a book chapter, a research paper, a sensitive essay — is often early-stage thinking you do not want sent anywhere. Amical ships with a local on-device model that runs without touching the network, which is the right default for the drafting phase. Switch to the cloud model later for the polishing pass where accuracy matters more than privacy.

What you'd dictate

Two thousand words of the new chapter drafted in a morning deep-work block.
Long-form essay draft on a hard topic, dictated in flow across two hours.
Research paper section drafted at thinking pace into the shared Google Doc.

Experience the future of dictation

Local and Cloud Models

Choose from powerful cloud-based AI models or run everything locally for maximum privacy and control. Switch seamlessly between providers to find the perfect balance of speed, accuracy, and security.

Icon
Icon
Icon
Icon

Custom Vocabulary

Customize the AI to recognize your specific terminology, jargon, and proper nouns for industry-specific accuracy and personalized transcription results.

Project PhoenixMcConaughey
CI/CD pipelinek8s
SOC2PostgreSQL
JiraROI metrics
Space
A
CtrlAltSpace

Custom Shortcuts

Create personalized voice commands and shortcuts to streamline your workflow and boost productivity with hands-free operation.

Multi Language Support

Transcribe and dictate in 100+ languages with native-level accuracy. Switch between languages seamlessly or use mixed-language dictation.

Frequently asked questions

Loved by builders

From San Francisco to Tokyo — what real users are saying about Amical.

ごめん、勝間さん。 ScribesよりAmicalだわ
This is really an amazing app, and I'm super impressed with how smooth it works, and their amazing support. It's just fast and accurate, and it formats the text depending on what application I'm using. This is really my go-to blathering app, and it makes my day so sweet and easy. Read on AppSumo →
【音声入力】 現状Windowsでも使えるおすすめはこの3つ。 ・Amical ・Aqua Voice ・Typeless 個人的には慣れもあるけどAqua Voiceが好き。Typelessは整形キツめなのが難点だけどUIUXが良い。Amicalはローカル完結で無料なのがデカい。 音声入力は移り変わりが激しいので年払いはしない方がいいです。
[Free] Amical for voice input is way too convenient. Reviewing the good and bad of Amical — and walking through installation too.

Translated

有益なアプリをありがとうございます☺️
r/LocalLLMu/todokanai_koi
There's also github.com/amicalhq/amical Switched to it a couple of weeks back, sleek UI and decent feature set. Works offline and on both windows and mac.
Amical - Open-source AI dictation app (@amical_app) Cossmology Profile: dub.sh/Vk7tPkn Key People: Haritabh Singh, Naomi Chopra (@NaomiChopra) #SpeechRecognition #OpenSource #OSS #COSS
ごめん、勝間さん。 ScribesよりAmicalだわ
This is really an amazing app, and I'm super impressed with how smooth it works, and their amazing support. It's just fast and accurate, and it formats the text depending on what application I'm using. This is really my go-to blathering app, and it makes my day so sweet and easy. Read on AppSumo →
【音声入力】 現状Windowsでも使えるおすすめはこの3つ。 ・Amical ・Aqua Voice ・Typeless 個人的には慣れもあるけどAqua Voiceが好き。Typelessは整形キツめなのが難点だけどUIUXが良い。Amicalはローカル完結で無料なのがデカい。 音声入力は移り変わりが激しいので年払いはしない方がいいです。
[Free] Amical for voice input is way too convenient. Reviewing the good and bad of Amical — and walking through installation too.

Translated

有益なアプリをありがとうございます☺️
r/LocalLLMu/todokanai_koi
There's also github.com/amicalhq/amical Switched to it a couple of weeks back, sleek UI and decent feature set. Works offline and on both windows and mac.
Amical - Open-source AI dictation app (@amical_app) Cossmology Profile: dub.sh/Vk7tPkn Key People: Haritabh Singh, Naomi Chopra (@NaomiChopra) #SpeechRecognition #OpenSource #OSS #COSS
ごめん、勝間さん。 ScribesよりAmicalだわ
This is really an amazing app, and I'm super impressed with how smooth it works, and their amazing support. It's just fast and accurate, and it formats the text depending on what application I'm using. This is really my go-to blathering app, and it makes my day so sweet and easy. Read on AppSumo →
【音声入力】 現状Windowsでも使えるおすすめはこの3つ。 ・Amical ・Aqua Voice ・Typeless 個人的には慣れもあるけどAqua Voiceが好き。Typelessは整形キツめなのが難点だけどUIUXが良い。Amicalはローカル完結で無料なのがデカい。 音声入力は移り変わりが激しいので年払いはしない方がいいです。
[Free] Amical for voice input is way too convenient. Reviewing the good and bad of Amical — and walking through installation too.

Translated

有益なアプリをありがとうございます☺️
r/LocalLLMu/todokanai_koi
There's also github.com/amicalhq/amical Switched to it a couple of weeks back, sleek UI and decent feature set. Works offline and on both windows and mac.
Amical - Open-source AI dictation app (@amical_app) Cossmology Profile: dub.sh/Vk7tPkn Key People: Haritabh Singh, Naomi Chopra (@NaomiChopra) #SpeechRecognition #OpenSource #OSS #COSS
ごめん、勝間さん。 ScribesよりAmicalだわ
This is really an amazing app, and I'm super impressed with how smooth it works, and their amazing support. It's just fast and accurate, and it formats the text depending on what application I'm using. This is really my go-to blathering app, and it makes my day so sweet and easy. Read on AppSumo →
【音声入力】 現状Windowsでも使えるおすすめはこの3つ。 ・Amical ・Aqua Voice ・Typeless 個人的には慣れもあるけどAqua Voiceが好き。Typelessは整形キツめなのが難点だけどUIUXが良い。Amicalはローカル完結で無料なのがデカい。 音声入力は移り変わりが激しいので年払いはしない方がいいです。
[Free] Amical for voice input is way too convenient. Reviewing the good and bad of Amical — and walking through installation too.

Translated

有益なアプリをありがとうございます☺️
r/LocalLLMu/todokanai_koi
There's also github.com/amicalhq/amical Switched to it a couple of weeks back, sleek UI and decent feature set. Works offline and on both windows and mac.
Amical - Open-source AI dictation app (@amical_app) Cossmology Profile: dub.sh/Vk7tPkn Key People: Haritabh Singh, Naomi Chopra (@NaomiChopra) #SpeechRecognition #OpenSource #OSS #COSS
Not sure why nobody's talking about it, but there's a free AI voice input app that's incredibly usable. It's called Amical — I use it daily.

Translated

tried amical (free & open source) alternative to whispr flow, aquavoice because they both charged me over $10 and the fact that it lets me run everything locally so nothing leaves my machine is crazyyy🤯
r/macappsu/IAM-rooted
nice comparison. been using amical lately and surprised it's not mentioned more. it's open source, runs locally or with cloud models, and actually formats stuff based on what app you're in. feels way more usable than just whisper or vosk on their own.
I was using VoiceDash, currently I'm using Blip AI, and now I'm testing Amical. So far, Amical is really, really good in recognizing my language and fantastic in recognizing the English language. I'm really impressed in this short period of time of using it. Read on AppSumo →
Amical for voice input is great — runs locally so it's super fast. I was on Aqua Voice but the 0.5s lag between speaking and seeing text was stressful every time. Local model accuracy is slightly lower but well within acceptable.

Translated

🎊 Big news! Amical @amical_app reached 1,000 stars on GitHub! High five! 🙌 Type 10x faster with AI-powered voice dictation openalternative.co/amical
Not sure why nobody's talking about it, but there's a free AI voice input app that's incredibly usable. It's called Amical — I use it daily.

Translated

tried amical (free & open source) alternative to whispr flow, aquavoice because they both charged me over $10 and the fact that it lets me run everything locally so nothing leaves my machine is crazyyy🤯
r/macappsu/IAM-rooted
nice comparison. been using amical lately and surprised it's not mentioned more. it's open source, runs locally or with cloud models, and actually formats stuff based on what app you're in. feels way more usable than just whisper or vosk on their own.
I was using VoiceDash, currently I'm using Blip AI, and now I'm testing Amical. So far, Amical is really, really good in recognizing my language and fantastic in recognizing the English language. I'm really impressed in this short period of time of using it. Read on AppSumo →
Amical for voice input is great — runs locally so it's super fast. I was on Aqua Voice but the 0.5s lag between speaking and seeing text was stressful every time. Local model accuracy is slightly lower but well within acceptable.

Translated

🎊 Big news! Amical @amical_app reached 1,000 stars on GitHub! High five! 🙌 Type 10x faster with AI-powered voice dictation openalternative.co/amical
Not sure why nobody's talking about it, but there's a free AI voice input app that's incredibly usable. It's called Amical — I use it daily.

Translated

tried amical (free & open source) alternative to whispr flow, aquavoice because they both charged me over $10 and the fact that it lets me run everything locally so nothing leaves my machine is crazyyy🤯
r/macappsu/IAM-rooted
nice comparison. been using amical lately and surprised it's not mentioned more. it's open source, runs locally or with cloud models, and actually formats stuff based on what app you're in. feels way more usable than just whisper or vosk on their own.
I was using VoiceDash, currently I'm using Blip AI, and now I'm testing Amical. So far, Amical is really, really good in recognizing my language and fantastic in recognizing the English language. I'm really impressed in this short period of time of using it. Read on AppSumo →
Amical for voice input is great — runs locally so it's super fast. I was on Aqua Voice but the 0.5s lag between speaking and seeing text was stressful every time. Local model accuracy is slightly lower but well within acceptable.

Translated

🎊 Big news! Amical @amical_app reached 1,000 stars on GitHub! High five! 🙌 Type 10x faster with AI-powered voice dictation openalternative.co/amical
Not sure why nobody's talking about it, but there's a free AI voice input app that's incredibly usable. It's called Amical — I use it daily.

Translated

tried amical (free & open source) alternative to whispr flow, aquavoice because they both charged me over $10 and the fact that it lets me run everything locally so nothing leaves my machine is crazyyy🤯
r/macappsu/IAM-rooted
nice comparison. been using amical lately and surprised it's not mentioned more. it's open source, runs locally or with cloud models, and actually formats stuff based on what app you're in. feels way more usable than just whisper or vosk on their own.
I was using VoiceDash, currently I'm using Blip AI, and now I'm testing Amical. So far, Amical is really, really good in recognizing my language and fantastic in recognizing the English language. I'm really impressed in this short period of time of using it. Read on AppSumo →
Amical for voice input is great — runs locally so it's super fast. I was on Aqua Voice but the 0.5s lag between speaking and seeing text was stressful every time. Local model accuracy is slightly lower but well within acceptable.

Translated

🎊 Big news! Amical @amical_app reached 1,000 stars on GitHub! High five! 🙌 Type 10x faster with AI-powered voice dictation openalternative.co/amical

Fast, Accurate, Context-aware and Private

Type 4x Faster with AI

Download Now