GET

/v1/schemas/fal/audio/fal-ai%2Felevenlabs%2Ftext-to-dialogue%2Feleven-v3

kind inputactivity audiohash 680109edextracted Jul 6, 2026version currentsource upstream spec ↗

Request body

6 properties · 1 required · 2 $defs
propertytypedescriptionconstraints
inputs*DialogueBlock[]A list of dialogue inputs, each containing text and a voice ID which will be converted into speech.
pronunciation_dictionary_locatorsPronunciationDictionaryLocator[]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 requestdefault: []
language_codestringLanguage code (ISO 639-1) used to enforce a language for the model. An error will be returned if language code is not supported by the model.nullable
seedintegerRandom seed for reproducibility.nullable
use_speaker_boostbooleanThis setting boosts the similarity to the original speaker. Using this setting requires a slightly higher computational load, which in turn increases latency.nullable
stabilitynumberDetermines how stable the voice is and the randomness between each generation. Lower values introduce broader emotional range for the voice. Higher values can result in a monotonous voice with limited emotion. Must be one of 0.0, 0.5, 1.0, else it will be rounded to the nearest value.0 ≤ n ≤ 1 · nullable

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/elevenlabs/text-to-dialogue/eleven-v3","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}