# Eleven v4 · Eleven V4

Generate speech, music and audio with Eleven v4 · Eleven V4 from fal through one Spiral API key. It runs in the background and returns audio. Pay as you go, with no subscription.

- Provider: fal
- Category: Audio
- Runs: In the background
- Returns: audio
- Tool id: `fal` / `elevenlabs/tts/eleven-v4`
- Page: https://spiral.ai/tools/fal/elevenlabs/tts/eleven-v4

## Pricing

Each item in `text` adds $0.104.

## Limits

- Longest queue wait: 1 hour
- Run deadline: 30 minutes
- Longest run, end to end: 255 minutes
- Largest inline input: 1 MB
- Largest input file: 2 GB
- Largest output: 5 GB

## Input

| Field | Kind | Allowed | Default | Description |
| --- | --- | --- | --- | --- |
| `text` (required) | text |  | — | The text to convert to speech. Supports audio tags such as [whispering] and IPA pronunciation enclosed in forward slashes. |
| `voice` | text |  | Rachel | The voice to use for speech generation |
| `stability` | number | 0 to 1 | 0.5 | Voice stability. Lower values allow more expressive delivery; higher values make delivery more consistent. |
| `similarity_boost` | number | 0 to 1 | 0.75 | How closely the output follows the reference voice. Higher values increase similarity but may reduce naturalness. |
| `seed` | number (whole) | 0 to 4294967295 | — | Seed for best-effort reproducibility. Identical output is not guaranteed. |
| `language_code` | text |  | — | Language code (ISO 639-1) for speech generation and text normalization. |
| `output_format` | one of | mp3_22050_32, mp3_44100_32, mp3_44100_64, mp3_44100_96, mp3_44100_128, mp3_44100_192, pcm_8000, pcm_16000, pcm_22050, pcm_24000, pcm_44100, pcm_48000, ulaw_8000, alaw_8000, opus_48000_32, opus_48000_64, opus_48000_96, opus_48000_128, opus_48000_192 | mp3_44100_128 | Output format of the generated audio. Formatted as codec_sample_rate_bitrate. |
| `apply_text_normalization` | one of | auto, on, off | auto | Whether to normalize text such as numbers and dates before generation. |
| `timestamps` | true or false |  | false | Whether to return character-level timing information with the generated audio. |

## Example

```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": "elevenlabs/tts/eleven-v4",
    "input": {
      "text": "[excited] Hello! Welcome to Eleven v4."
    }
  }'
```

Try it in the Playground: https://spiral.ai/start?provider=fal&model=elevenlabs%2Ftts%2Feleven-v4

## Common questions

### Eleven v4 · Eleven V4

**How much does Eleven v4 · Eleven V4 cost?**

Each item in `text` adds $0.104. You pay as you go from one Spiral balance, with no subscription, and a failed run is not charged.

**How do I use Eleven v4 · Eleven V4 through an API?**

Send `POST /v1/runs` with `"provider": "fal"`, `"model": "elevenlabs/tts/eleven-v4"` and the input fields on this page, using one Spiral API key. It runs in the background: poll the run, or name a webhook to be told when it finishes.

**Do I need an account with fal to use Eleven v4 · Eleven V4?**

No. Spiral runs it on its own fal account and charges your Spiral balance.

**Can my AI agent use Eleven v4 · Eleven V4?**

Yes. Agents find and run it through Spiral's MCP server, CLI or agent skill, with the same API key.

