# Voice Delivery

> Describe how a designed voice speaks: its pace, its emotion and a voice-acting style, such as Documentary Narrator. Nodaro adds it to Voice Design.

Source: https://nodaro.ai/docs/nodes/creative-controls/voice-delivery

The **Voice Delivery** picker describes how a voice speaks: its pace, its emotion and its voice-acting style. You choose options such as Measured, Reassuring and Documentary Narrator, and Nodaro adds the description to the voice description of the [Voice Design](https://nodaro.ai/docs/nodes/audio/voice-design) node you connect it to. The picker never calls a model, so it costs no credits.

- Found in: Creative Controls › Music & Voice
- Output: text
- API type: `voice-delivery`

## When to use it
- Design a narrator for a documentary, an audiobook or a fairy tale.
- Give a character voice a clear attitude, such as Menacing, Sarcastic, Cheerful or Stoic.
- Match a format, such as a Podcaster, a Sportscaster, an Infomercial or an AI Assistant.
- Set the pace of speech, from Very Slow and Drawl to Rapid-fire and Frenetic.

## How to use it
### Add the picker

Open the node picker on the **Audio** tab and choose **Creative Controls › Music & Voice › Voice Delivery**.

### Describe the delivery

Click the node and choose a **Pace**, an **Emotion** and an **Archetype**. Every part is optional.

### Connect it

Drag from the picker's output to the **Audio style** input of a [Voice Design](https://nodaro.ai/docs/nodes/audio/voice-design) node.

### Run Voice Design

The description is added to the node's voice description when it runs.

Workflow: Voice Character says who speaks and Voice Delivery says how, on the same Voice Design node.

- Voice Character → Voice Design (audio style)
- Voice Delivery → Voice Design (audio style)

## Settings
| Setting | What it does |
| --- | --- |
| **Pace** | One speaking pace, such as Slow, Measured, Moderate, Punchy, Brisk or Rapid-fire. |
| **Emotion** | One emotional tone, such as Warm, Reassuring, Urgent, Excited, Wistful or Playful. |
| **Archetype** | One voice-acting style, such as Newscaster, Documentary Narrator, Audiobook Narrator, Radio DJ, Villain or Mentor. |
| **Custom text (before)** | Your own words, added before the description, for example `pause, gather composure`. |
| **Custom text (after)** | Your own words, added after the description, for example `trail off`. |
| **Prompt hint** | **Full** (default) adds the longer description. **Compact** adds only the short terms. See [Full or Compact](https://nodaro.ai/docs/nodes/creative-controls#full-or-compact). |

A new node starts empty and adds nothing until you pick. The parts are built into one phrase in a fixed order: the pace and the archetype as a delivery style, then the emotion as a tone. Parts you leave empty are skipped.

To see the exact words the picker will add, switch the node to the **Prompt** or **Both** display mode. The settings panel shows the same text under **Will inject into prompt**.

## Where the description goes

On [Voice Design](https://nodaro.ai/docs/nodes/audio/voice-design), the description is added to the voice description. The preview text that the voice speaks is never changed. [Text to Audio](https://nodaro.ai/docs/nodes/audio/text-to-audio) makes sound effects, so it ignores voice pickers and shows a warning.

You can also connect the picker to a [Text](https://nodaro.ai/docs/nodes/automate/text) or [Combine Text](https://nodaro.ai/docs/nodes/automate/combine-text) node to use the words in a longer text.

## Every pace, emotion and archetype

Filter by part or search by name. The words under each name are the term the picker adds in **Compact** mode.

**Pace**

- Very Slow
- Slow
- Drawl: `drawled`
- Measured
- Moderate
- Punchy
- Brisk
- Rapid
- Rapid-fire
- Frenetic
- Halting

**Emotion**

- Neutral
- Cheerful
- Warm
- Reassuring
- Compassionate
- Somber
- Stoic
- Urgent
- Frantic
- Anxious
- Scared
- Excited
- Enthusiastic
- Wistful
- Melancholic
- Menacing
- Angry
- Sarcastic
- Smug
- Playful
- Flirty
- Intimate
- Seductive

**Archetype**

- Newscaster
- TV Anchor
- Documentary Narrator
- Nature Narrator: `nature documentary narrator`
- Fairy-Tale Narrator
- Audiobook Narrator
- Podcaster
- Talk Show Host
- Radio DJ
- ASMR
- Sportscaster
- Auctioneer
- Preacher
- Politician
- Lawyer
- Professor
- Infomercial
- Voice Actor
- Drag Queen
- Villain
- Hero: `heroic`
- Mentor
- Comedian: `comedic`
- Stand-up Comic
- Drill Sergeant
- Meditation Guide
- Yoga Instructor
- Noir Detective
- Wizard
- Robot: `robotic`
- AI Assistant
- Virtual Assistant

## Tips
- **Pair it with Voice Character.** [Voice Character](https://nodaro.ai/docs/nodes/creative-controls/voice-character) sets the age, gender, language, accent and timbre. Voice Delivery adds the pace, the emotion and the style.
- **Compare variations.** Change one part, such as the emotion, run Voice Design again, and compare the previews.
- **Hear the whole voice.** The preview text of Voice Design must be 100 to 1,000 characters. Write enough to hear the voice across different sounds and sentences.

## Frequently asked questions

### What does the Voice Delivery picker do?

It describes how a voice speaks, such as a measured documentary narrator with a reassuring tone, and adds that description to the voice description of a Voice Design node.

### Does the Voice Delivery picker cost credits?

No. Pickers only change the prompt. You pay only for the Voice Design node that uses it.

### What is the difference between Voice Delivery and Voice Character?

Voice Character describes who is speaking, such as the age, the gender and the accent. Voice Delivery describes how they speak, such as the pace, the emotion and the style. Use both on one Voice Design node.

### What is an archetype?

A familiar voice-acting style, such as Newscaster, Audiobook Narrator, Radio DJ, Meditation Guide or Noir Detective. It gives the voice a recognizable way of speaking.