GET

/v1/schemas/fal/audio/google/gemini-3.8-flash-tts

kind inputactivity audiohash dc7e6ec2…extracted Nov 10, 2026version currentsource upstream spec ↗
fieldrecorded source
schemaSource linked above.

upstream-spec

Source trace
bfa671e69355c4e64cb324a0f52eb1a09e2a6de331d9276185bc28fac04dcb0b
{
  "fetchedAt": 1794286801,
  "extractorVersion": "2",
  "verifiedAt": null
}

Request body

6 properties · 0 required · 2 $defs
propertytypedescriptionconstraints
voiceenumPrebuilt voice for single-speaker speech.Achernar | Achird | Algenib | Algieba | Alnilam | Aoede · +24 more · default: "Kore"
speakersSpeakerConfig[]Exactly two distinct speaker aliases and their prebuilt voices for dialogue.items ≥ 2 · items ≤ 2 · nullable
style_instructionsstringDelivery style, separate from the spoken transcript. Applies to all turns unless overridden.nullable
promptstringVerbatim text for single-speaker speech. Put delivery directions in style_instructions; inline vocal events may use <laugh> or <sigh>. For dialogue, omit prompt and provide speakers and turns instead. The provider limits the complete input to 8,192 tokens.nullable
enable_safety_checkerbooleanAuthorized callers may set false to request relaxed screening.default: true
turnsSpeechTurn[]Ordered dialogue turns, each identifying a configured speaker.items ≥ 1 · nullable

Types

2 $defs

SpeakerConfigobject

voice*enumPrebuilt voice for this speaker.Achernar | Achird | Algenib | Algieba | Alnilam | Aoede · +24 more
speaker_id*stringSpeaker alias used in each turn.length ≥ 1

SpeechTurnobject

text*stringVerbatim transcript for this turn.length ≥ 1
speaker_id*stringAlias of a configured speaker.length ≥ 1
style_instructionsstringOptional delivery style for this turn.nullable

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"google/gemini-3.8-flash-tts","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}