GET

/v1/schemas/fal/audio/xai/tts/v1

Accept:

kind inputactivity audiohash 10593259…extracted Oct 9, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `2e09dd373f03a1c7ea50d88f14d27f4662cd3c5723b55dfa1cdac1291f801552` { "fetchedAt": 1791522002, "extractorVersion": "1", "verifiedAt": null }

Request body

5 properties · 1 required · 1 $defs

property	type	description	constraints
text*	string	The text to convert to speech. Maximum 15,000 characters. Supports speech tags for expressive delivery: inline tags like [laugh], [pause], [sigh] and wrapping tags like <whisper>text</whisper>, <slow>text</slow>.	length ≥ 1 · length ≤ 15000
output_format	OutputFormat	Output format configuration. Defaults to MP3 at 24 kHz / 128 kbps.
language	enum	BCP-47 language code or 'auto' for automatic detection. Supported: en, zh, fr, de, hi, id, it, ja, ko, pt-BR, pt-PT, ru, es-MX, es-ES, tr, vi, bn, ar-EG, ar-SA, ar-AE.	auto \| en \| ar-EG \| ar-SA \| ar-AE \| bn · +15 more · default: "auto"
voice	enum	Built-in xAI voice to use for synthesis.	carina \| zagan \| helix \| orion \| luna \| iris · +22 more · default: "eve"
enable_safety_checker	boolean	Authorized callers may set false to request relaxed screening.	default: true

Types

1 $defs

OutputFormatobject

Output format configuration for the TTS API.

sample_rate	enum	Sample rate in Hz.	8000 \| 16000 \| 22050 \| 24000 \| 44100 \| 48000 · default: 24000
bit_rate	enum	Bit rate in bps. Only applicable for MP3 codec. Defaults to 128000 for MP3.	32000 \| 64000 \| 96000 \| 128000 \| 192000 · nullable
codec	enum	Audio codec. Supported: mp3, wav, pcm, mulaw, alaw.	mp3 \| wav \| pcm \| mulaw \| alaw · default: "mp3"

Validate a payload

before you spend tokens

shell

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