GET

/v1/schemas/fal/audio/fal-ai%2Fminimax%2Fspeech-2.6-hd

kind inputactivity audiohash 12257a1c…extracted Oct 17, 2026version currentsource upstream spec ↗

Request body

8 properties · 1 required · 4 $defs
propertytypedescriptionconstraints
prompt*stringText to convert to speech. Paragraph breaks should be marked with newline characters. **NOTE**: You can customize speech pauses by adding markers in the form `<#x#>`, where `x` is the pause duration in seconds. Valid range: `[0.01, 99.99]`, up to two decimal p…length ≥ 1 · length ≤ 10000
voice_settingVoiceSettingVoice configuration settings
language_boostenumEnhance recognition of specified languages and dialectsChinese | Chinese,Yue | English | Arabic | Russian | Spanish · +32 more · nullable
output_formatenumFormat of the output content (non-streaming only)url | hex · default: "hex"
normalization_settingLoudnessNormalizationSettingLoudness normalization settings for the audio
enable_safety_checkerbooleanAuthorized callers may set false to request relaxed screening.default: true
audio_settingAudioSettingAudio configuration settings
pronunciation_dictPronunciationDictCustom pronunciation dictionary for text replacementnullable

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/minimax/speech-2.6-hd","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}