# Suno Prompt for Spoken Word: Narration & Talking Intros (2026) | Lyro Music

> How to prompt spoken word tracks in Suno and Udio: [Spoken] tags, narration voice, backing music that stays out of the way, and a full example prompt.

Source: https://lyromusic.com/prompts/spoken-word

# How to write a Suno prompt for spoken word

Updated 2026-09-22

Name the anchor as spoken word or narration, describe the voice as talking rather than singing, and keep the backing music sparse so words stay clear. Try: "spoken word, low sparse beat, minor key piano loop, soft brushed drums, deep calm speaking voice, close mic, moody, 85 BPM".

Use the [Spoken] section tag in the lyrics box to mark parts that should be talked, not sung, and switch to [Verse] or [Chorus] for any sung sections.

### The prompt

spoken word, low sparse beat, minor key piano loop, soft brushed drums, deep calm speaking voice, close mic, moody, 85 BPM

[Make it on Lyro Music$9$3 first month](https://lyromusic.com/start?genre=hiphop)[Open the prompt generator](https://lyromusic.com/ai-music-prompt-generator)

## More promptsCopy and paste

### Narration over boom bap

spoken word, boom bap beat, dusty vinyl texture, laid-back drums, upright bass, calm speaking voice, close mic, 88 BPM, minor key

Use it when: for a hip-hop style narration with a lo-fi, reflective feel

### Talking intro then song

spoken word intro, no drums, sparse piano, distant strings, low speaking voice, then full band enters, mid tempo, 90 BPM, minor key

Use it when: when you want the track to open with talking before the song properly starts

### Spoken word with sung hook

spoken verse, sung chorus, boom bap drums, warm bass, minor key sample loop, calm speaking voice verses, smooth sung hook, 92 BPM

Use it when: for a track that alternates between talked verses and a melodic chorus

### Minimal beat poetry

spoken word, finger snaps only, no bass, sparse brushed hats, close mic speaking voice, dry room sound, slow, 80 BPM, minor key

Use it when: for a stripped-back, coffeehouse style poetry reading feel

### Dark narration

spoken word, dark ambient pads, deep sub bass, slow sparse drums, low raspy speaking voice, distant reverb, moody, 82 BPM, minor key

Use it when: for a tense, storytelling or true-crime style narration mood

### Female narrator over trap hats

spoken word, trap hats, deep 808 bass, minor key synth loop, breathy female speaking voice, close mic, moody, 95 BPM

Use it when: for a modern trap-adjacent spoken word track with a female narrator

### Leave out

- singing
- melody
- auto-tune
- loud drums
- distorted vocal
- percentages or dB numbers

## What does the [Spoken] tag actually do?

The [Spoken] tag is a section marker, similar to [Verse] or [Chorus], that tells the model to read that block of text as talked rather than sung. It works often but not always, since it is a convention the model follows rather than a strict rule. Write the lines in the lyrics box as plain sentences with normal punctuation, not rhyming couplets, since spoken word reads more like prose or slam poetry than song lyrics.

If the model starts singing a [Spoken] section anyway, try shortening the lines or adding a clearer instruction in the style box, such as "spoken word, no singing, talking voice throughout".

## How do I describe a narration voice in the style box?

Use plain voice-timbre words rather than genre jargon: calm, deep, raspy, breathy, low, or close mic for an intimate, near-the-microphone feel. These are the kind of descriptors models respond to reliably, unlike vaguer words like "smooth" or claims about age, which are closer to a coin flip.

Pair the voice description with a mix note if you want a particular feel, for example "deep calm speaking voice, close mic, dry room sound" for something intimate, or "low raspy speaking voice, distant reverb" for something more cinematic and separated from the listener.

## What tempo and backing music suits spoken word?

Spoken word usually sits over a slower, sparser beat than a sung hip-hop track, because the words need room to breathe and the beat should not compete with the pacing of speech. A boom bap style backing (a laid-back, sample-based hip-hop drum feel) at 85 to 95 BPM in a minor key, often G minor or D minor, works well as a default, but you can go slower and stripped-back for a more meditative reading.

| Feel | Tempo | Backing |
|---|---|---|
| Reflective, lo-fi | 85-90 BPM | dusty vinyl texture, soft drums, upright bass |
| Minimal, poetry reading | 78-85 BPM | finger snaps, sparse piano, no bass |
| Tense, narrative | 80-88 BPM | dark pads, deep sub bass, slow drums |

## Can spoken word switch between talking and singing in the same track?

Yes, and it is common to talk the verses and sing the chorus, or to open with a spoken intro before the song proper begins. Mark each section clearly with [Spoken] for talked parts and [Verse] or [Chorus] for sung parts, and describe both voice styles in the style box, for example "calm speaking voice verses, smooth sung hook", so the model has separate instructions for each.

Keep the backing music consistent across both, usually the same tempo and key, so the switch between talking and singing feels like one track rather than two stitched together.

## Lyrics skeleton

Original, for structure

[Spoken]
I used to think the city slept at night
but it just changes shift and keeps on moving
every streetlight is a small confession
every corner keeps a story it’s not telling

[Chorus]
We stay awake, we stay awake
waiting on a sign that never breaks

## Common mistakes

- Writing rhymed, sung-style lyrics under a [Spoken] tag: write the lines as plain prose or loose free verse instead, since rhyme patterns tend to pull the model back towards singing.
- Leaving the beat too busy or loud, which buries the spoken voice: describe the backing as sparse or low and keep drums soft so the words stay the focus.
- Forgetting to describe the voice at all: without a voice description many models default to a generic sung tone, so always add words like calm, deep, raspy or breathy speaking voice.
- Mixing too many moods in one prompt, such as calm and aggressive together: pick one dominant mood and let the voice and backing both support it.
- Expecting the whole track to stay spoken with no singing creeping in: if this happens, add an explicit note such as "no singing, talking voice throughout" in the style box.

## Questions

### How do I stop Suno from singing my spoken word lyrics?

Use the [Spoken] section tag, write the lines as plain prose rather than rhyming verse, and add "no singing, talking voice throughout" to the style box. This works often but not always, since section tags are a convention the model follows rather than a guaranteed rule, so you may need to regenerate if it still sings.

### What BPM should a spoken word hip-hop track be?

Most spoken word over a hip-hop style backing sits at 85 to 95 BPM, the same range as boom bap, since it gives the words room to land without dragging. Go slower, around 78 to 85 BPM, for a more meditative or poetry-reading feel with minimal drums.

### Can I make the whole track just talking with no music?

Describe the backing as very sparse or near-silent, such as "no drums, no bass, distant ambient texture only", rather than asking for total silence, since the model still expects some sonic bed. For a true no-music voice recording, a separate voice or narration tool would suit better than a music generator.

### How do I get a deep, calm narrator voice instead of a rapper voice?

Use plain timbre words such as "deep calm speaking voice, close mic" rather than genre words like "rap", since rap implies rhythmic delivery and rhyme, while narration implies a steadier, prose-like read. Avoid words like "smooth" alone, as they are less reliable than concrete descriptors like deep, raspy or breathy.

### Should I use minor or major key for spoken word?

Minor keys, often G minor or D minor, suit most spoken word since they carry a naturally reflective or moody tone that supports narration. Major keys work if the piece is meant to feel warm or hopeful, but state the mood clearly in the prompt either way so the backing matches the words.

### Can Lyro Music make spoken word tracks?

Yes, describe the track as spoken word or narration with a voice description and a backing style, and Lyro Music turns that description into a mixed and mastered song. Spoken vocal lines route through the same lyrics pipeline as sung lyrics, using Google's Lyria 3 Pro, while beat-only backing can use ACE-Step 1.5.

### How long should spoken word lines be per section?

Keep lines to roughly one short sentence each, since long, syllable-heavy lines make it harder for the model to pace the delivery naturally against the beat. Break longer thoughts across two or three shorter [Spoken] lines rather than one dense block.

Related: [Hip-hop prompts: tempo, keys and eight more prompts](https://lyromusic.com/prompts/hip-hop), [How to write a Suno prompt for a female voice](https://lyromusic.com/prompts/female-vocals), [How to write a Suno prompt for a male voice](https://lyromusic.com/prompts/male-vocals), [How to write a Suno prompt for a duet](https://lyromusic.com/prompts/duet), [Suno prompt for choir vocals: what to write](https://lyromusic.com/prompts/choir), [Suno prompt for a cappella: how to get voice only](https://lyromusic.com/prompts/a-cappella), [How do you write a Suno prompt for background vocals?](https://lyromusic.com/prompts/background-vocals)