GET

/v1/schemas/elevenlabs/audio/v1/text-to-dialogue/with-timestamps?kind=output

kind outputactivity audiohash 5b81c69a…extracted Jul 6, 2026version currentsource upstream spec ↗

Response body

4 properties · 2 required · 2 $defs
propertytypedescriptionconstraints
audio_base64*stringBase64 encoded audio data
voice_segments*VoiceSegment[]Voice segments for the audio
alignmentCharacterAlignmentResponseModelTimestamp information for each character in the original textnullable
normalized_alignmentCharacterAlignmentResponseModelTimestamp information for each character in the normalized textnullable

Types

2 $defs

CharacterAlignmentResponseModelobject

characters*string[]
character_start_times_seconds*number[]
character_end_times_seconds*number[]

VoiceSegmentobject

voice_id*stringThe voice ID used for this segment
start_time_seconds*numberStart time of this voice segment
end_time_seconds*numberEnd time of this voice segment
character_start_index*integerStart index in the characters array
character_end_index*integerEnd index in the characters array (exclusive)
dialogue_input_index*integerLine of the dialogue (script) that this segment is a part of.

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"elevenlabs","endpointId":"v1/text-to-dialogue/with-timestamps","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}