[Integrations](https://spiral.ai/integrations) › [Codex](https://spiral.ai/integrations/codex) › [Seed Audio 1.0](https://spiral.ai/integrations/codex/seed-audio-1-0)

# How to Use Seed Audio 1.0 in Codex

Seed Audio 1.0 turns a script or scene description into dialogue, sound effects, and ambience together. Use it for expressive narration or short audio scenes, with up to two minutes of output per generation.

|  |  |
| --- | --- |
| Model | Seed Audio 1.0 |
| Available through | fal |
| Category | Audio |
| Price | $0.244 per minute of output audio, for outputs of 2 minutes or less. |
| Returns | audio |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Seed Audio 1.0 in Codex

- Use Seed Audio 1.0 to turn the opening conversation in our game's dialogue files into an audio preview under 60 seconds. Preserve the lines, give each speaker a distinct voice, and add quiet tavern ambience.
- Read the onboarding flow in this project and draft a 45-second narration using only behavior confirmed in the code. Generate it with Seed Audio 1.0 in a calm, clear voice without background effects.
- Use Seed Audio 1.0 to generate a spoken preview of the first tutorial scene in our scripts. Keep it under 90 seconds, preserve the instructions, and specify measured delivery with pauses between steps.
- Take the approved English and Chinese welcome strings from our localization files. Use Seed Audio 1.0 with multilingual mode to create separate short readings with a warm voice and no background sound.
- Find the two-character encounter script in this project and prepare an audio prompt under 2,048 characters. Use Seed Audio 1.0 to generate a scene under one minute with contrasting voices, quiet wind, and a closing door sound.

## How to set up Seed Audio 1.0 in Codex

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

### Use Spiral's MCP server

1. **Add the hosted server**

```bash
codex mcp add spiral --url https://api.spiral.ai/mcp
```

2. **Sign in**: Codex opens the browser: sign in to Spiral and click Authorize. No API key. `codex mcp list` then shows Spiral.

```bash
codex mcp login spiral
```

### Use the Spiral skill

1. **Send Codex 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 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 Seed Audio 1.0**: 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": "bytedance/seed-audio-1.0",
    "input": {
      "prompt": "Here'\''s a quick look at your day: you'\''ve got three meetings, one lunch, and just enough time in between to grab a coffee and relax."
    }
  }'
```

Then paste one of the prompts above: Codex finds Seed Audio 1.0 on Spiral, shows the price and runs it.

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

## Seed Audio 1.0 tools and prices

- [Seed Audio 1.0 · Text to Audio](https://spiral.ai/tools/fal/bytedance/seed-audio-1.0) (fal): $0.244 per minute of output audio, for outputs of 2 minutes or less.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| voice |  | — | Voice to use for synthesis: either a preset voice name or a cloned voice id. |
| audio_urls |  | — | Up to 3 reference audio URLs, referenced in prompt as @Audio1, @Audio2, @Audio3. Each clip: up to 30s, 10MB, wav/mp3/pcm/ogg_opus. |
| image_url |  | — | A single reference image URL (jpeg/png/webp, up to 10MB). Cannot be combined with audio references. |
| output_format | wav, mp3, pcm, ogg_opus | mp3 | Output audio format. |
| sample_rate | 8000, 16000, 24000, 32000, 44100, 48000 | 24000 | Sample rate of the output audio in Hz. |
| speed | 0.5 to 2 | 1 | Speech speed. 1.0 is normal speed, 0.5 is half speed, 2.0 is double speed. |

## What can you do with Seed Audio 1.0 in Codex?

Turn project dialogue and tutorial scripts into audio you can review alongside the product. Seed Audio 1.0 can supply spoken delivery, effects, and ambience for short scenes.

### Game dialogue previews

Turn a short conversation into a playable scene with distinct voices, delivery notes, and location sounds. Review how the exchange feels before editing it into the game.

### Short audio dramas

Create a scene in which spoken lines, footsteps, and room ambience carry the story. Keep each generation within two minutes.

### Product tutorial narration

Generate spoken explanations from an approved script. Specify a clear voice, measured delivery, and no background effects.

### Podcast openings

Create a brief host introduction with explicit delivery notes and a restrained background atmosphere.

### Multilingual voiceovers

Generate separate readings of approved translations with multilingual mode. Keep the intended tone and pacing explicit in each script.

### Narrated promotional scenes

Combine a short spoken message with a recognizable setting and a few sound cues, such as a shop opening or a train arriving.

### Recurring character recordings

Use clean voice references to direct new lines for recurring characters. Assign each reference to the intended speaker in the script.

### Spoken daily briefings

Convert an approved daily summary into concise narration with clear section pauses and an explicit speaking style.

## Overview

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

## Seed Audio 1.0 in other agents

- [Amp](https://spiral.ai/integrations/amp/seed-audio-1-0)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/seed-audio-1-0)
- [Claude](https://spiral.ai/integrations/claude-desktop/seed-audio-1-0)
- [Claude Code](https://spiral.ai/integrations/claude-code/seed-audio-1-0)
- [Cline](https://spiral.ai/integrations/cline/seed-audio-1-0)
- [Cursor](https://spiral.ai/integrations/cursor/seed-audio-1-0)
- [Devin](https://spiral.ai/integrations/devin/seed-audio-1-0)
- [dots](https://spiral.ai/integrations/dots/seed-audio-1-0)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/seed-audio-1-0)
- [Gemini](https://spiral.ai/integrations/gemini/seed-audio-1-0)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/seed-audio-1-0)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/seed-audio-1-0)
- [goose](https://spiral.ai/integrations/goose/seed-audio-1-0)
- [Grok](https://spiral.ai/integrations/grok/seed-audio-1-0)
- [Grok Build](https://spiral.ai/integrations/grok-build/seed-audio-1-0)
- [Hermes](https://spiral.ai/integrations/hermes/seed-audio-1-0)
- [Instinct](https://spiral.ai/integrations/instinct/seed-audio-1-0)
- [Manus](https://spiral.ai/integrations/manus/seed-audio-1-0)
- [Muse](https://spiral.ai/integrations/muse/seed-audio-1-0)
- [Muse Code](https://spiral.ai/integrations/muse-code/seed-audio-1-0)
- [n8n](https://spiral.ai/integrations/n8n/seed-audio-1-0)
- [Notion](https://spiral.ai/integrations/notion/seed-audio-1-0)
- [OpenClaw](https://spiral.ai/integrations/openclaw/seed-audio-1-0)
- [opencode](https://spiral.ai/integrations/opencode/seed-audio-1-0)
- [Perplexity](https://spiral.ai/integrations/perplexity/seed-audio-1-0)
- [Raycast](https://spiral.ai/integrations/raycast/seed-audio-1-0)
- [VS Code](https://spiral.ai/integrations/vscode/seed-audio-1-0)
- [Windsurf](https://spiral.ai/integrations/windsurf/seed-audio-1-0)
- [Zapier](https://spiral.ai/integrations/zapier/seed-audio-1-0)

## More Codex guides

- [Scribe v3](https://spiral.ai/integrations/codex/scribe-v3)
- [Seed Speech TTS 2.0](https://spiral.ai/integrations/codex/seed-speech-tts-2-0)
- [Scribe v2](https://spiral.ai/integrations/codex/scribe-v2)
- [Sonilo V1.1 Text to Music](https://spiral.ai/integrations/codex/sonilo-v1-1-text-to-music)
- [SAM Audio Visual Separation](https://spiral.ai/integrations/codex/sam-audio-visual-separation)
- [Sonilo v1.1 Text to Sound Effects](https://spiral.ai/integrations/codex/sonilo-v1-1-text-to-sound-effects)

## Questions about Seed Audio 1.0 in Codex

**Can Codex use Seed Audio 1.0?**

Yes. Add Spiral to Codex as an MCP server, and Codex can find and run Seed Audio 1.0 like any built-in tool.

**How much does Seed Audio 1.0 cost in Codex?**

$0.244 per minute of output audio, for outputs of 2 minutes or less. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Codex plan is separate.

**Do I need a fal account to use Seed Audio 1.0 in Codex?**

No. Spiral runs Seed Audio 1.0 on its own fal account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Seed Audio 1.0 in Codex?**

About two minutes: add the hosted server, then sign in.

**Does Codex wait while Seed Audio 1.0 runs?**

Seed Audio 1.0 runs in the background. Codex starts the run, checks on it and gives you the audio when it's ready.

**What is Seed Audio 1.0 good at?**

Use it for expressive narration and scenes where dialogue, effects, and ambience need to work together. Short dramas, game conversations, and narrated promos are practical starting points.

**How long can Seed Audio 1.0 generate?**

The documented limit is two minutes per generation. Plan longer productions as separate scenes, and keep each prompt within fal's documented 2,048-character limit.

**Can Seed Audio 1.0 generate languages other than English?**

ByteDance documents support for more than 20 languages. Choose multilingual mode for non-English speech or scripts that mix languages.

**How should I write a Seed Audio 1.0 prompt?**

Write a short audio script: establish the setting, describe each speaker's voice and delivery, then supply the exact lines. Add specific background sounds and a clear ending.

**Can Seed Audio 1.0 place every sound at an exact time?**

ByteDance says timing control currently focuses mainly on character dialogue. Treat exact placement of effects, ambience, and music as something to check and adjust during editing.

