GET

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

Accept:

kind outputactivity audiohash a78cd9ba…extracted Jul 6, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. Source trace `56793d52b38081086c43910ec1916ff4bb286322250511820c239e4f46831396` { "fetchedAt": 1783328734, "extractorVersion": "1", "verifiedAt": null }

Response body

4 properties · 2 required · 2 $defs

property	type	description	constraints
audio_base64*	string	Base64 encoded audio data
voice_segments*	VoiceSegment[]	Voice segments for the audio
alignment	CharacterAlignmentResponseModel	Timestamp information for each character in the original text	nullable
normalized_alignment	CharacterAlignmentResponseModel	Timestamp information for each character in the normalized text	nullable

Types

2 $defs

CharacterAlignmentResponseModelobject

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

VoiceSegmentobject

voice_id*	string	The voice ID used for this segment
start_time_seconds*	number	Start time of this voice segment
end_time_seconds*	number	End time of this voice segment
character_start_index*	integer	Start index in the characters array
character_end_index*	integer	End index in the characters array (exclusive)
dialogue_input_index*	integer	Line 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/stream/with-timestamps","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}