GET

/v1/schemas/fal/audio/bytedance%2Fseed-audio-1.0

kind inputactivity audiohash b8837c13extracted Jul 21, 2026version currentsource upstream spec ↗

Request body

10 properties · 1 required · 0 $defs
propertytypedescriptionconstraints
prompt*stringPrompt or text to synthesize. Reference audio inputs by order with @Audio1, @Audio2, @Audio3.length ≤ 2048
multilingualbooleanUse the multilingual model variant, which handles non-English and mixed-language prompts better.default: false
volumenumberVolume. 1.0 is normal volume, 0.5 is half, 2.0 is double.0.5 ≤ n ≤ 2 · default: 1
image_urlstringA single reference image URL (jpeg/png/webp, up to 10MB). Cannot be combined with audio references.nullable
voicestringVoice to use for synthesis: either a preset voice name or a cloned voice id.nullable
speednumberSpeech speed. 1.0 is normal speed, 0.5 is half speed, 2.0 is double speed.0.5 ≤ n ≤ 2 · default: 1
output_formatenumOutput audio format.wav | mp3 | pcm | ogg_opus · default: "mp3"
pitchintegerVoice pitch shift in semitones. 0 is normal pitch, -12 lowers by one octave, 12 raises by one octave.-12 ≤ n ≤ 12 · default: 0
sample_rateenumSample rate of the output audio in Hz.8000 | 16000 | 24000 | 32000 | 44100 | 48000 · default: 24000
audio_urlsstring[]Up to 3 reference audio URLs, referenced in prompt as @Audio1, @Audio2, @Audio3. Each clip: up to 30s, 10MB, wav/mp3/pcm/ogg_opus.items ≤ 3

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"bytedance/seed-audio-1.0","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}