[Integrations](https://spiral.ai/integrations) › [Instinct](https://spiral.ai/integrations/instinct) › [xAI Text to Speech](https://spiral.ai/integrations/instinct/xai-text-to-speech)

# How to Use xAI Text to Speech in Instinct

xAI Text to Speech turns written scripts into narration for tutorials, spoken articles, and character dialogue. Its speech tags let you add pauses, whispers, and slower delivery within a passage.

|  |  |
| --- | --- |
| Model | xAI Text to Speech |
| Available through | fal |
| Category | Audio |
| Price | Each item in `text` adds $0.0195. |
| Returns | audio |
| Runs | In the background |
| Setup | About 2 minutes, with a Spiral API key |

## Prompts to try with xAI Text to Speech in Instinct

- Every weekday morning, prepare a spoken briefing from verified public astronomy news published in the previous day. Keep it under 2,000 characters and generate it with xAI Text to Speech, pausing between stories.
- Each Monday, write a 120-word beginner Spanish listening exercise about an everyday activity. Generate normal and slower readings with xAI Text to Speech, keeping the wording identical.
- Each Friday, summarize changes announced on the public Python release page that week. Generate a spoken update with xAI Text to Speech only when new information is available, with pauses between releases.
- Every evening, write a 150-word original bedtime story with a clear ending. Generate it with xAI Text to Speech, using slower delivery for the final two complete sentences.
- On the first day of each month, prepare a short introduction to the next month's observable meteor showers from verified astronomy sources. Generate English and Spanish narration with xAI Text to Speech using the same built-in voice.

## How to set up xAI Text to Speech in Instinct

Pick the way that suits you. Each takes about two minutes.

### Use the Spiral skill

1. **Send Instinct this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use Spiral's MCP server

1. **Create an API key**: In the console, open API keys and create a key for Instinct. Copy it.

2. **Send Instinct this message**: Instinct reads Spiral's skill and asks for your API key.

```text
set up https://spiral.ai/SKILL.md
```

3. **Give Instinct the key**: When Instinct asks for the key, add it where Instinct keeps secrets, never in the chat itself.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run xAI Text to Speech**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "fal",
    "model": "xai/tts/v1",
    "input": {
      "text": "Hello! This is xAI text to speech, brought to you by Fal AI."
    }
  }'
```

Then paste one of the prompts above: Instinct finds xAI Text to Speech on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/instinct

## xAI Text to Speech tools and prices

- [xAI Text to Speech](https://spiral.ai/tools/fal/xai/tts/v1) (fal): $0.0195 per 1,000 characters of `text`. Rounded up to the next 1,000 characters, minimum 1,000.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| voice | carina, zagan, helix, orion, luna, iris, altair, zenith, perseus, helios, lux, kepler, rigel, cosmo, celeste, ursa, sirius, lumen, castor, naksh, atlas, aurora, liora, ara, eve, leo, rex, sal | eve | Built-in xAI voice to use for synthesis. |
| language | auto, en, ar-EG, ar-SA, ar-AE, bn, zh, fr, de, hi, id, it, ja, ko, pt-BR, pt-PT, ru, es-MX, es-ES, tr, vi | auto | BCP-47 language code or 'auto' for automatic detection. Supported: en, zh, fr, de, hi, id, it, ja, ko, pt-BR, pt-PT, ru, es-MX, es-ES, tr, vi, bn, ar-EG, ar-SA, ar-AE. |
| output_format |  | — | Output format configuration. Defaults to MP3 at 24 kHz / 128 kbps. |

## What can you do with xAI Text to Speech in Instinct?

Produce recurring spoken briefings, lessons, and updates with xAI Text to Speech. Have the scheduled agent prepare a concise script from its available information and divide longer narration into sections.

### Spoken articles

Turn an edited article into narration. Divide scripts longer than 15,000 characters at section boundaries.

### Product tutorial narration

Generate spoken instructions for a walkthrough, placing pauses between actions so listeners can follow along.

### Translated training narration

Narrate prepared translations of a training lesson using the same built-in voice across supported languages.

### Character dialogue drafts

Try a scene with whispered phrases, sighs, or laughter before choosing the delivery for each line.

### Podcast narration drafts

Convert an approved introduction or scripted segment into speech, then review the pacing before editing the episode.

### Spoken daily briefings

Have an agent prepare a short briefing from verified updates, then generate narration with pauses between topics.

### Practice listening exercises

Generate a normal reading and a slower reading of the same short passage for language practice.

## Overview

- [fal](https://spiral.ai/providers/fal)
- [All Instinct guides](https://spiral.ai/integrations/instinct)

## xAI Text to Speech in other agents

- [Amp](https://spiral.ai/integrations/amp/xai-text-to-speech)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/xai-text-to-speech)
- [Claude](https://spiral.ai/integrations/claude-desktop/xai-text-to-speech)
- [Claude Code](https://spiral.ai/integrations/claude-code/xai-text-to-speech)
- [Cline](https://spiral.ai/integrations/cline/xai-text-to-speech)
- [Codex](https://spiral.ai/integrations/codex/xai-text-to-speech)
- [Cursor](https://spiral.ai/integrations/cursor/xai-text-to-speech)
- [Devin](https://spiral.ai/integrations/devin/xai-text-to-speech)
- [dots](https://spiral.ai/integrations/dots/xai-text-to-speech)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/xai-text-to-speech)
- [Gemini](https://spiral.ai/integrations/gemini/xai-text-to-speech)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/xai-text-to-speech)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/xai-text-to-speech)
- [goose](https://spiral.ai/integrations/goose/xai-text-to-speech)
- [Grok](https://spiral.ai/integrations/grok/xai-text-to-speech)
- [Grok Build](https://spiral.ai/integrations/grok-build/xai-text-to-speech)
- [Hermes](https://spiral.ai/integrations/hermes/xai-text-to-speech)
- [Manus](https://spiral.ai/integrations/manus/xai-text-to-speech)
- [Muse](https://spiral.ai/integrations/muse/xai-text-to-speech)
- [Muse Code](https://spiral.ai/integrations/muse-code/xai-text-to-speech)
- [n8n](https://spiral.ai/integrations/n8n/xai-text-to-speech)
- [Notion](https://spiral.ai/integrations/notion/xai-text-to-speech)
- [OpenClaw](https://spiral.ai/integrations/openclaw/xai-text-to-speech)
- [opencode](https://spiral.ai/integrations/opencode/xai-text-to-speech)
- [Perplexity](https://spiral.ai/integrations/perplexity/xai-text-to-speech)
- [Raycast](https://spiral.ai/integrations/raycast/xai-text-to-speech)
- [VS Code](https://spiral.ai/integrations/vscode/xai-text-to-speech)
- [Windsurf](https://spiral.ai/integrations/windsurf/xai-text-to-speech)
- [Zapier](https://spiral.ai/integrations/zapier/xai-text-to-speech)

## More Instinct guides

- [Zonos2](https://spiral.ai/integrations/instinct/zonos2)
- [Bria Fibo Lite structured prompt](https://spiral.ai/integrations/instinct/bria-fibo-lite-structured-prompt)
- [Whisper Large](https://spiral.ai/integrations/instinct/whisper-large)
- [Bria Fibo structured edit instructions](https://spiral.ai/integrations/instinct/bria-fibo-structured-edit-instructions)
- [VEED Clean Audio](https://spiral.ai/integrations/instinct/veed-clean-audio)
- [Bria Fibo structured image prompt](https://spiral.ai/integrations/instinct/bria-fibo-structured-image-prompt)

## Questions about xAI Text to Speech in Instinct

**Can Instinct use xAI Text to Speech?**

Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run xAI Text to Speech like any built-in tool.

**How much does xAI Text to Speech cost in Instinct?**

Each item in `text` adds $0.0195. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Instinct plan is separate.

**Do I need a fal account to use xAI Text to Speech in Instinct?**

You need no fal account. Instinct uses one Spiral API key for every tool, and Spiral runs xAI Text to Speech on its own fal account.

**How long does it take to set up xAI Text to Speech in Instinct?**

About two minutes: create an API key, then send Instinct this message, then give Instinct the key.

**Does Instinct wait while xAI Text to Speech runs?**

xAI Text to Speech runs in the background. Instinct starts the run, checks on it and gives you the audio when it's ready.

**What is xAI Text to Speech useful for?**

Use it to turn finished scripts into spoken articles, tutorials, or dialogue. Speech tags help when a passage needs a pause, a whispered aside, or a change in pace.

**Can xAI Text to Speech narrate a long article?**

Yes, but the listed endpoint limits each request to 15,000 characters. Split longer scripts at paragraph or section boundaries before generating the audio.

**How do I add pauses or change the delivery?**

Put [pause] where a break belongs. Wrap a passage in <whisper>...</whisper> or <slow>...</slow> to change how that passage is spoken.

**How should I apply speech tags?**

Wrap complete phrases instead of tagging individual words. Start with one passage, listen to the result, and adjust the tagged span before generating the full script.

**Can the same voice narrate different languages?**

Yes. Any built-in voice can speak any supported language, so you can keep the same voice selection across translated scripts.

