Poetry Recitation to Text That Knows Where Lines End
Upload a poetry reading and Musely generates verse text with real line breaks, stanza spacing, and every spoken word preserved. 5 forms, 4 presets, 51 languages.
Musely Poetry Recitation to Text Converter is an AI transcription tool that turns spoken poetry into properly formatted verse text. Unlike prose transcription that breaks lines at punctuation, Musely detects natural pauses in the delivery to determine line endings — preserving the poet's intended visual structure. Powered by Seed-ASR 2.0 with smoothing disabled, it preserves every spoken word exactly across 51 languages. Supports 5 poetic forms (Free Verse, Sonnet, Haiku, Spoken Word, Traditional) and 4 output presets (Formatted Poem, Annotated Reading with performance notes, Published Format for literary submission, Phonetic Singalong with stress marks). Optional line numbers enable academic citation. Recordings up to 30 minutes.
Under the Hood
🤖Transcription Engine
Verse Formatting
Convert Poetry Recitation in 3 Steps
Upload Your Poetry Recording
Drag and drop your audio or video file (MP3, WAV, M4A, MP4, MOV) into Musely. Supports files up to 500 MB and 30 minutes. Select the recited language from 51 options for best accuracy with archaic vocabulary and unusual phonetic patterns.
Set Poem Details and Choose a Preset
Optionally enter the poem title, poet name, and poetry form (Free Verse, Sonnet, Haiku, Spoken Word, or Traditional). Choose a preset: Formatted Poem for clean verse, Annotated Reading for performance notes, Published Format for literary submission, or Phonetic Singalong with stress marks for practice. Toggle stanza breaks and line numbers.
Get Your Formatted Verse Text
Musely applies verse-aware formatting — placing line breaks at natural pauses, inserting blank lines at stanza boundaries, and preserving every spoken word with smoothing disabled. Review the result and download as Markdown, TXT, or DOCX for publication, teaching, or archival use.
Who Uses Musely Poetry Recitation to Text
Capture improvised performances as publication-ready verse
I improvise sets at slam competitions and needed a way to capture the exact words with my performed line breaks. Otter.ai flattened everything into prose paragraphs. Musely's Spoken Word form preserves my rhythm and repetition patterns. The Annotated Reading preset even marks where I paused and where I built emphasis.
Cite specific lines from recorded poet readings
For my seminar paper I needed transcripts of recorded Keats readings for close analysis. Musely's Published Format preset with line numbers enabled lets me cite 'line 9' precisely. The Sonnet form organizes the output as quatrains and a couplet automatically. My TA was impressed.
Record model readings with annotated delivery notes
I record my own model readings of poems and use the Annotated Reading preset to share delivery notes with my students. Pauses, emphasis, and tempo changes all get bracketed, so students studying for the AP exam understand exactly where the emotional weight lands.
Archive famous poet recordings with verbatim preservation
Our archive has reel-to-reel recordings of poets reading their own work. Musely's disabled smoothing preserves unconventional syntax and deliberate fragmentation that a cleaned transcript would erase. The Published Format preset produces archive-ready documents that meet our cataloging standards.
Review student competition sets with performance analysis
My students compete in regional slam. I record their practice sets and use Musely's Annotated Reading preset to mark every pause, emphasis, and tempo change. Then we review the notes together before the next practice. It's transformed how I coach performance delivery.
Translate verse recitations while keeping poetic structure
I teach comparative literature across Spanish, French, and English poetry traditions. Musely translates verse recitations while preserving line breaks and rhythmic effect — not the flat prose translations other tools produce. My students can study original and translated versions side by side.
Musely vs. General Transcription Tools for Poetry
| Feature | Musely | Otter.ai | Rev.com | Whisper (OpenAI) |
|---|---|---|---|---|
| Line Break Detection | ✓ Pause-based / matches delivery | ✗ Sentence-based (prose) | ✗ Sentence-based (prose) | ✗ Sentence-based (prose) |
| Stanza Detection | ✓ Automatic from pacing | ✗ Not available | ✗ Not available | ✗ Not available |
| Poetry Form Support | ✓ 5 forms (Free Verse / Sonnet / Haiku / Spoken Word / Traditional) | ✗ No form awareness | ✗ No form awareness | ✗ No form awareness |
| Verbatim Smoothing | ✓ Disabled / every word preserved | ✗ On by default | ⚠ Human editing may alter | ⚠ Punctuation normalized |
| Performance Annotations | ✓ Annotated preset with tone notes | ✗ Not available | ✗ Not available | ✗ Not available |
| Line Numbers | ✓ Optional for academic use | ✗ Not available | ✗ Not available | ✗ Not available |
| Phonetic Guides | ✓ Phonetic Singalong with stress marks | ✗ Not available | ✗ Not available | ✗ Not available |
What Poets and Teachers Say
4.9/5 based on 820 reviews
“I improvise slam sets and Otter.ai flattened everything into prose paragraphs, erasing my performed line breaks. Musely's Spoken Word form preserves my rhythm and repetition, and the Annotated Reading preset marks exactly where I paused and where I built emphasis. My coach uses it to review every practice.”
“Our poetry archive has hundreds of reel-to-reel recordings of poets reading their own work. Musely's disabled smoothing preserves unconventional syntax and deliberate fragmentation that a cleaned transcript would erase. The Published Format produces archive-ready documents that meet our cataloging standards.”
“For my graduate seminar paper I needed transcripts of Keats recordings with line numbers. Musely's Published Format with line numbers enabled lets me cite 'line 9' precisely. The Sonnet form organizes the output as quatrains and a couplet automatically. Saved me 15 hours of manual formatting.”
Frequently Asked Questions
Musely poetry recitation to text converter is the only tool that formats spoken poetry as verse rather than prose. It detects line breaks from natural pauses in delivery, identifies stanza boundaries from pacing, and supports 5 poetic forms (Free Verse, Sonnet, Haiku, Spoken Word, Traditional) across 51 languages with verbatim smoothing disabled.
Otter.ai and Rev.com format output as prose paragraphs, inserting line breaks only at sentence-ending punctuation. Poetry line breaks follow the poet's breath and pause pattern, not grammar. Musely detects natural pauses to place line breaks where the poet intended them, with smoothing disabled to preserve every spoken word.
Yes. When a poet pauses between groups of lines for 1.5 seconds or longer, Musely inserts a blank line to mark a stanza boundary. This captures the poem's thematic structure from recitation pacing. Stanza break detection can be toggled off for recordings with irregular pacing that shouldn't be interpreted as structure.
Musely supports five form modes: Free Verse (break lines at natural pauses), Sonnet (three quatrains and a couplet, or two quatrains and a sestet), Haiku (three lines with 5-7-5 syllable awareness), Spoken Word (performance-driven line breaks), and Traditional (preserve end-rhyme alignment). Selecting Unknown lets the structure emerge from the delivery itself.
Musely supports recordings up to 30 minutes with a 500 MB file size limit. Most individual poems and short recital sets fall well within this. For longer poetry events or anthology recordings, process each poem or section as a separate file. A typical 5-minute recitation processes in under 60 seconds.
No. Smoothing is disabled for poetry transcription, so every spoken word is preserved exactly — including repetition, fragmentation, incomplete phrases, and non-standard grammar intentional to the poem's design. Musely does not correct informal language, merge short phrases, or reorder words for readability.