# ElevenLabs Multilingual v2 Text to Speech

Turn text into speech and audio with ElevenLabs Multilingual v2 Text to Speech through one Spiral API key. Turns text into lifelike speech in a chosen voice across 29 languages, a stable model suited to long-form narration. It runs in the background and returns audio. Pay as you go, with no subscription.

- Provider: ElevenLabs
- Category: Audio
- Runs: In the background
- Returns: audio
- Released: 2023-08-22
- Tool id: `elevenlabs` / `eleven_multilingual_v2`
- Page: https://spiral.ai/tools/elevenlabs/eleven_multilingual_v2

## Pricing

$0.104 per 1,000 characters of text.

## 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 that will get converted into speech. |
| `voice_id` (required) | text |  | — | Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices. |
| `seed` | number (whole) |  | — | If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. |
| `next_text` | text |  | — | The text that comes after the text of the current request. |
| `audio_effects` | JSON |  | — | Audio effects applied to the generated audio. |
| `language_code` | text |  | — | Language code (ISO 639-1) used to enforce a language for the model and text normalization. |
| `output_format` | one of | alaw_8000, mp3_22050_32, mp3_24000_48, mp3_44100_128, mp3_44100_192, mp3_44100_32, mp3_44100_64, mp3_44100_96, opus_48000_128, opus_48000_192, opus_48000_32, opus_48000_64, opus_48000_96, pcm_16000, pcm_22050, pcm_24000, pcm_32000, pcm_44100, pcm_48000, pcm_8000, ulaw_8000, wav_16000, wav_22050, wav_24000, wav_32000, wav_44100, wav_48000, wav_8000 | mp3_44100_128 | Output format of the generated audio. |
| `previous_text` | text |  | — | The text that came before the text of the current request. |
| `use_pvc_as_ivc` | true or false |  | — | Whether to use the IVC version of a professional voice. This may improve expressiveness and reduce latency. |
| `voice_settings` | JSON |  | — | Voice settings overriding stored settings for the given voice. They are applied only on the given request. |
| `next_request_ids` | list |  | — | A list of request_id of the samples that come after this generation. next_request_ids is especially useful for maintaining the speech's continuity when regenerating a sample that has had some audio quality issues. |
| `previous_request_ids` | list |  | — | A list of request_id of the samples that were generated before this generation. |
| `apply_text_normalization` | one of | auto, on, off | auto | This parameter controls text normalization with three modes: 'auto', 'on', and 'off'. |
| `optimize_streaming_latency` | number (whole) |  | — | You can turn on latency optimizations at some cost of quality. |
| `apply_language_text_normalization` | true or false |  | false | This parameter controls language text normalization. |
| `pronunciation_dictionary_locators` | JSON |  | — | A list of pronunciation dictionary locators (id, version_id) to be applied to the text. They will be applied in order. You may have up to 3 locators per request |

## 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": "elevenlabs",
    "model": "eleven_multilingual_v2",
    "input": {
      "text": "<text>",
      "voice_id": "<voice_id>"
    }
  }'
```

Try it in the Playground: https://spiral.ai/start?provider=elevenlabs&model=eleven_multilingual_v2

## Common questions

### ElevenLabs Multilingual v2 Text to Speech

**How much does ElevenLabs Multilingual v2 Text to Speech cost?**

$0.104 per 1,000 characters of text. You pay as you go from one Spiral balance, with no subscription, and a failed run is not charged.

**How do I use ElevenLabs Multilingual v2 Text to Speech through an API?**

Send `POST /v1/runs` with `"provider": "elevenlabs"`, `"model": "eleven_multilingual_v2"` 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 ElevenLabs to use ElevenLabs Multilingual v2 Text to Speech?**

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

**Can my AI agent use ElevenLabs Multilingual v2 Text to Speech?**

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

