Step 1
Bring the source
Type an idea, use browser speech recognition, or upload supported audio for transient transcription.
AI content repurposing
Turn audio into social media posts, then edit every word
Any supported recording — an interview, a workshop, a voice memo you talked through in the car — can become a post, a thread, a newsletter draft, and a five-slide carousel. Upload it, read the transcript, fix what the model misheard, then generate.
- No account needed to draft
- Every output editable
- Source snapshot kept with each version
What you actually get
Exactly which files work, what happens to them, and what you get back.
- Supported formats and sizeMP3 (audio/mpeg), M4A (audio/mp4, audio/x-m4a), WAV, WebM, and OGG, up to 15 MB. The allowlist is enforced in the browser and again on the server before any bytes reach the model.
- Nothing is retainedThe recording is forwarded for transcription and discarded. DraftLark stores no audio, and raw AI credentials are never exposed to the browser.
- The transcript is yours to editIt arrives in the same source field a typed note would use, with a live word and sentence count, so you can trim, correct, and shorten before generating.
- Bounded, visible allowancesTranscription and generation each have a daily allowance shown on the Usage view. When one runs out, local drafting, editing, copying, and exporting all keep working.
How the workflow works
Three steps in one screen. Nothing here is a simulated demo — it is the studio you land in when you open DraftLark.
Step 2
Choose the formats
Generate bounded post, thread, newsletter, and static carousel drafts using the selected voice controls.
Step 3
Review and export
Compare drafts with the retained source snapshot, edit every output, and export text or static HTML only after human review.
Where DraftLark stops
Useful software starts with an accurate promise. These limits apply before you begin.
- Files over 15 MB, and formats outside the allowlist, are rejected before upload.
- Transcription is one shot per file: no diarisation, no timestamps, no editing of the audio itself.
- Upload and transcription require a signed-in Google account.
- DraftLark output is a draft, not fact-checked, original-by-guarantee, or publication-ready content.
- Uploaded audio is sent transiently for transcription and is not retained by DraftLark.
- The product does not claim scheduling, publishing, video generation, social-platform integrations, or a long-form blog output.
Audio to Social Media Posts: common questions
Which audio formats are accepted?
MP3, M4A, WAV, WebM, and OGG, up to 15 MB per file. Anything else is refused in the browser with a clear message before the upload starts.
Does DraftLark record audio for me?
No. It transcribes files you already have, and separately supports live dictation through your browser's own speech recognition. It does not capture or store a recording.
What happens if transcription fails?
You get an explicit message and the source field is left untouched, so you can re-select the same file and try again without losing anything you had already written.