Skip to content
deckdrill

Your keys

Keys stay in this browser. Each request sends the key through our relay to that one provider; nothing is stored or logged.

Writing cards

Leave blank for claude-sonnet-5-5.

Voices

Most natural voices, and the only option for cloning your own voice (Starter plan or higher).

No voice key? Drills can still play live with your device's own voices.

Turn your flashcards into audio drills you can actually speak along with.

deckdrill writes Anki decks and builds hour-long Pimsleur- and Glossika-style drills from them, in native voices or a clone of your own. You bring the API keys, so you pay the providers directly and nothing is stored here.

Open the studioBrowse the demo decks

if I'd sold the farm that first winter, I'd be in the city today

  1. en la ciudad
  2. hoy estaría en la ciudad
  3. la granja aquel primer invierno, hoy estaría en la ciudad
  4. Si hubiera vendido la granja aquel primer invierno, hoy estaría en la ciudad.
From the Coulda Woulda Shoulda drill, spoken in a cloned voice

How it works

  1. 1

    Get your cards

    Describe a topic and a grammar focus and your own AI key writes the cards, or import a deck you already have in Anki.

  2. 2

    Choose the voices

    Native neural voices from ElevenLabs or Azure, your own cloned voice for most of the sentences, or your device's built-in voices for free.

  3. 3

    Render the drills

    Long Pimsleur- and Glossika-style MP3s with pauses timed to each sentence, ready for a commute or a run.

  4. 4

    Study in Anki

    Download an .apkg with the same audio on every card, or send it straight to Anki on your computer.

Two ways to drill the same deck

Pimsleur-style

Each new card: English cue → the sentence → a backward build-up from the end (each chunk with a pause to repeat) → slow, normal, slow, normal. Then the card comes back as a recall prompt (English cue, a pause to say it yourself, the answer) 1, 4 and 10 cards later, and once more in a final recall pass.

Built on retrieval practice and spacing, the two most robust findings in memory research. Building up from the end keeps the sentence's natural final intonation on every repetition.

The 30-card Quedar demo runs about 16 minutes in this style.

Glossika-style

Two passes through the deck. Each card: English cue → the sentence → slow → the sentence again, each with a pause to repeat. No breakdown.

High volume of whole sentences at natural speed — good for listening fluency and rhythm once the pieces are familiar.

The 30-card Quedar demo runs about 7 minutes in this style.

What the research says
  • Spacing: distributed review beats massed review (Cepeda et al., 2006 meta-analysis).
  • Retrieval: trying to produce the answer beats re-hearing it (Roediger & Karpicke, 2006) — which is why the recall pause matters more than the repetition.
  • Expanding vs. equal intervals is less settled than Pimsleur claimed (Karpicke & Roediger, 2007); what matters most is a short first delay and long delays eventually.
  • Pure parroting without meaning transferred poorly in the old Audio-Lingual method — drill meaningful sentences with recall, not lists.

Hear the sentences in your own voice

Record about two minutes, confirm the voice is yours, and it's cloned into your own ElevenLabs account. Then let it speak most of the sentences while a native voice takes the rest, so you hear both the target and yourself saying it right.

Set up your voice

Questions

Do you store my API keys?

No. Keys stay in your browser (this tab only, unless you tick “remember on this device”). Each request sends the key to our stateless relay, which forwards it to that one provider and keeps nothing.

Can I use it without any keys?

Yes. The demo decks and audio are free to browse. Drills can play live with your device's built-in voices, and exported decks can use Anki's own text-to-speech. Saving drill MP3s needs an ElevenLabs or Azure Speech key; writing new cards needs an Anthropic, OpenAI or Gemini key.

How do I use my own voice?

On the Your voice page, record about two minutes of clear speech (or upload a file), confirm it's your voice, and it's cloned into your own ElevenLabs account (Starter plan or higher). Then pick it as the main speaker in the studio — for example on 75% of cards, with another voice on the rest.

What does a drill cost?

You pay the TTS provider directly, per character. A 30-card deck of full sentences is roughly 4,000–7,000 characters for the target-language speaker, depending on sentence length, plus about a third of that for the English cues. Both styles share the same lines — each sentence, its slow version and its chunks are made once — and the studio shows the exact count before you render. Rendered lines are cached in your browser, so re-rendering or exporting the deck afterwards costs nothing extra.

Will it work with my existing Anki decks?

Yes — import any .apkg (including the newer compressed format). The studio reads the front and the first line of the back of each note.

Which languages?

Card generation and drills work for Spanish (Mexico), Spanish (US), Spanish (Spain), Portuguese (Brazil), French, Italian, German, Polish. English is the cue language.

Ask the assistant

Ask how the drills work, what a deck will cost, or tell us about a problem and the assistant will email us.

Contact

Bugs, ideas, or a deck you'd like to see.