GET

/v1/schemas/fal/audio/fal-ai/index-tts-2/text-to-speech

kind inputactivity audiohash 21856142…extracted Oct 9, 2026version currentsource upstream spec ↗
fieldrecorded source
schemaSource linked above.

upstream-spec

Source trace
c2adf7b86209b0ee3554edd4be9aa3d3e51644c50a77b6ee659733e0d498f054
{
  "fetchedAt": 1791522002,
  "extractorVersion": "1",
  "verifiedAt": null
}

Request body

8 properties · 2 required · 1 $defs
propertytypedescriptionconstraints
audio_url*stringThe audio file to generate the speech from.
prompt*stringThe speech prompt to generate
emotional_audio_urlstringThe emotional reference audio file to extract the style from.nullable
enable_safety_checkerbooleanAuthorized callers may set false to request relaxed screening.default: true
should_use_prompt_for_emotionbooleanWhether to use the `prompt` to calculate emotional strengths, if enabled it will overwrite the `emotional_strengths` values. If `emotion_prompt` is provided, it will be used to instead of `prompt` to extract the emotional style.nullable
emotion_promptstringThe emotional prompt to influence the emotional style. Must be used together with should_use_prompt_for_emotion.nullable
emotional_strengthsEmotionalStrengthsThe strengths of individual emotions for fine-grained control. nullable
strengthnumberThe strength of the emotional style transfer. Higher values result in stronger emotional influence.0 ≤ n ≤ 1 · default: 1

Types

1 $defs

EmotionalStrengthsobject

happynumberStrength of happiness emotion0 ≤ n ≤ 1 · default: 0
sadnumberStrength of sadness emotion0 ≤ n ≤ 1 · default: 0
disgustednumberStrength of disgust emotion0 ≤ n ≤ 1 · default: 0
afraidnumberStrength of fear emotion0 ≤ n ≤ 1 · default: 0
surprisednumberStrength of surprise emotion0 ≤ n ≤ 1 · default: 0
melancholicnumberStrength of melancholic emotion0 ≤ n ≤ 1 · default: 0
angrynumberStrength of anger emotion0 ≤ n ≤ 1 · default: 0
calmnumberStrength of calm emotion0 ≤ n ≤ 1 · default: 0

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/index-tts-2/text-to-speech","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}