creative.speech

Providers

Provider	Status
fal	live

Billing

Unit: per_1k_characters · unmatched results billed: no
Priced by the length of the text, pro rata: eleven-turbo $0.0875 per 1,000 characters, eleven-v3 $0.175. A 600-character script (about 40 seconds of speech) quotes $0.0525 on eleven-turbo. The exact quote is reserved before execution. The audio URL is temporary; store what you keep.

The exact quote is returned by /v1/inspect before every call and held with headroom on execution. The quote is the price floor: if the provider's actual cost overruns it, the run bills the overrun at the same rate, never above the hold. The unused part of every hold is released.

Run it

curl https://api.routergrowth.com/v1/run \
  -H "Authorization: Bearer $ROUTERGROWTH_API_KEY" \
  -d '{
    "capability": "creative.speech",
    "input": { "text": "..." },
    "routing": {"provider": "auto"}
  }'

Input schema

{
  "properties": {
    "language": {
      "description": "Two-letter ISO 639-1 code to force the language, for example en or fr. Omit to let the model detect it.",
      "type": "string"
    },
    "model": {
      "default": "eleven-turbo",
      "description": "per 1,000 characters: eleven-turbo $0.0875 (fast, takes speed), eleven-v3 $0.175 (most expressive)",
      "enum": [
        "eleven-turbo",
        "eleven-v3"
      ],
      "type": "string"
    },
    "speed": {
      "description": "eleven-turbo only: 0.7 (slower) to 1.2 (faster), default 1",
      "type": "number"
    },
    "stability": {
      "description": "0 (more expressive) to 1 (more even), default 0.5",
      "type": "number"
    },
    "text": {
      "description": "The script to speak, up to 5,000 characters per call",
      "type": "string"
    },
    "timestamps": {
      "default": false,
      "description": "Return per-word timings, for captions synced to the voice",
      "type": "boolean"
    },
    "voice": {
      "description": "A voice name: Aria, Roger, Sarah, Laura, Charlie, George, Callum, River, Liam, Charlotte, Alice, Matilda, Will, Jessica, Eric, Chris, Brian, Daniel, Lily or Bill. Omit for the model\u0027s default voice.",
      "type": "string"
    }
  },
  "required": [
    "text"
  ],
  "type": "object"
}

Normalized output fields

model · characters · audio · timestamps