GET

/v1/schemas/fal/audio/async/tts-pro/v1.0

Accept:

kind inputactivity audiohash 79c67918…extracted Aug 5, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. Source trace `bad2cb9ce20fa54ed171c5d4d9bf5352df5cd918ae600b6b6da63824fb50fb63` { "fetchedAt": 1785906144, "extractorVersion": "1", "verifiedAt": null }

Request body

4 properties · 2 required · 2 $defs

property	type	description	constraints
voice*	Voice	Voice to use for synthesis.
transcript*	string	Text to convert to speech.
output_format	OutputFormat	Audio output configuration.
language	enum	Force synthesis in a specific language (ISO 639-1).	en \| fr \| es \| de \| it \| pt · nullable

Types

2 $defs

OutputFormatobject

bit_rate	integer	Output bit rate. Only used when container is 'mp3'.	32000 ≤ n ≤ 320000 · nullable
container	enum	Output audio container format.	mp3 \| raw · default: "mp3"
sample_rate	integer	Output sample rate in Hz.	8000 ≤ n ≤ 48000 · default: 44100
encoding	enum	PCM encoding. Only used when container is 'raw'.	pcm_s16le \| pcm_f32le \| pcm_mulaw · nullable

Voiceobject

Voice selection: by `name` from the predefined catalogue, or by raw `id`.

name

enum

Predefined voice, chosen by name. Ignored when `id` is set.

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"async/tts-pro/v1.0","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}