# MiniMax Speech 2.6 [Turbo] · Text To Speech 2.6 Turbo

Turn text into speech and audio with MiniMax Speech 2.6 [Turbo] · Text To Speech 2.6 Turbo 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` / `fal-ai/minimax/speech-2.6-turbo`
- Page: https://spiral.ai/tools/fal/fal-ai/minimax/speech-2.6-turbo

## Pricing

Each item in `prompt` adds $0.078.

## 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 |
| --- | --- | --- | --- | --- |
| `prompt` (required) | text |  | — | Text to convert to speech. Paragraph breaks should be marked with newline characters. **NOTE**: You can customize speech pauses by adding markers in the form `<#x#>`, where `x` is the pause duration in seconds. Valid range: `[0.01, 99.99]`, up to two decimal places. Pause markers must be placed between speakable text segments and cannot be used consecutively. |
| `voice_setting` | JSON |  | {"vol":1,"pitch":0,"speed":1,"voice_id":"Wise_Woman","english_normalization":false} | Voice configuration settings |
| `audio_setting` | JSON |  | — | Audio configuration settings |
| `language_boost` | one of | Chinese, Chinese,Yue, English, Arabic, Russian, Spanish, French, Portuguese, German, Turkish, Dutch, Ukrainian, Vietnamese, Indonesian, Japanese, Italian, Korean, Thai, Polish, Romanian, Greek, Czech, Finnish, Hindi, Bulgarian, Danish, Hebrew, Malay, Slovak, Swedish, Croatian, Hungarian, Norwegian, Slovenian, Catalan, Nynorsk, Afrikaans, auto | — | Enhance recognition of specified languages and dialects |
| `output_format` | one of | url, hex | hex | Format of the output content (non-streaming only) |
| `pronunciation_dict` | JSON |  | — | Custom pronunciation dictionary for text replacement |
| `normalization_setting` | JSON |  | — | Loudness normalization settings for the 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": "fal-ai/minimax/speech-2.6-turbo",
    "input": {
      "prompt": "Hello world! Welcome MiniMax'\''s new text to speech model <#0.1#> Speech 2.6 Turbo, now available on Fal!"
    }
  }'
```

Try it in the Playground: https://spiral.ai/start?provider=fal&model=fal-ai%2Fminimax%2Fspeech-2.6-turbo

## Common questions

### MiniMax Speech 2.6 [Turbo] · Text To Speech 2.6 Turbo

**How much does MiniMax Speech 2.6 [Turbo] · Text To Speech 2.6 Turbo cost?**

Each item in `prompt` adds $0.078. You pay as you go from one Spiral balance, with no subscription, and a failed run is not charged.

**How do I use MiniMax Speech 2.6 [Turbo] · Text To Speech 2.6 Turbo through an API?**

Send `POST /v1/runs` with `"provider": "fal"`, `"model": "fal-ai/minimax/speech-2.6-turbo"` 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 MiniMax Speech 2.6 [Turbo] · Text To Speech 2.6 Turbo?**

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

**Can my AI agent use MiniMax Speech 2.6 [Turbo] · Text To Speech 2.6 Turbo?**

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

