ElevenLabs TTS V4

https://mcp.app.layer.ai/mcp

execute_forge({
  "base_model_id": "eleven-labs-tts-v4",
  "prompt": "A heavy stone door grinding open in a dungeon",
  "batch_size": 1
})

# Start the generation — returns an inference id straight away.
curl -X POST https://api.app.layer.ai/api/v2/workspaces/$WORKSPACE_ID/base-models/elevenlabs-tts-v4/inferences \
  -H "Authorization: Bearer $LAYER_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
        "prompt": "A heavy stone door grinding open in a dungeon"
      }'

# Poll until status is "complete" — the response then carries the asset URLs.
curl https://api.app.layer.ai/api/v2/workspaces/$WORKSPACE_ID/inferences/$INFERENCE_ID \
  -H "Authorization: Bearer $LAYER_TOKEN"

prompt

stringrequired

The text the voice speaks.

seed

integer

The starting point for the model's randomness. The same seed and settings give the same result.

stability

numberdefault 0.50–1

How steady the voice stays. Lower is more expressive, higher more consistent.

similarity_boost

numberdefault 0.750–1

How closely the voice keeps to the original speaker.

text_normalization

enumdefault AUTOAUTO, ON, OFF

Spell out numbers, dates and abbreviations as words before speaking them.

prompt_language

string

The language the voice speaks in.