GET

/v1/schemas/elevenlabs/audio/v1%2Ftext-to-voice%2Fdesign

kind inputactivity audiohash 78e9ed43extracted Jul 6, 2026version currentsource upstream spec ↗

Request body

14 properties · 1 required · 0 $defs
propertytypedescriptionconstraints
voice_description*stringDescription to use for the created voice.length ≥ 20 · length ≤ 1000
model_idenumModel to use for the voice generation. Possible values: eleven_multilingual_ttv_v2, eleven_ttv_v3.eleven_multilingual_ttv_v2 | eleven_ttv_v3 · default: "eleven_multilingual_ttv_v2"
textstringText to generate, text length has to be between 100 and 1000.length ≥ 100 · length ≤ 1000 · nullable
auto_generate_textbooleanWhether to automatically generate a text suitable for the voice description.default: false
loudnessnumberControls the volume level of the generated voice. -1 is quietest, 1 is loudest, 0 corresponds to roughly -24 LUFS.-1 ≤ n ≤ 1 · default: 0.5
seedintegerRandom number that controls the voice generation. Same seed with same inputs produces same voice.0 ≤ n ≤ 2147483647 · nullable
guidance_scalenumberControls how closely the AI follows the prompt. Lower numbers give the AI more freedom to be creative, while higher numbers force it to stick more to the prompt. High numbers can cause voice to sound artificial or robotic. We recommend to use longer, more deta…0 ≤ n ≤ 100 · default: 5
stream_previewsbooleanDetermines whether the Text to Voice previews should be included in the response. If true, only the generated IDs will be returned which can then be streamed via the /v1/text-to-voice/:generated_voice_id/stream endpoint.default: false
should_enhancebooleanWhether to enhance the voice description using AI to add more detail and improve voice generation quality. When enabled, the system will automatically expand simple prompts into more detailed voice descriptions. Defaults to Falsedefault: false
remixing_session_idstringThe remixing session id.nullable
remixing_session_iteration_idstringThe id of the remixing session iteration where these generations should be attached to. If not provided, a new iteration will be created.nullable
qualitynumberHigher quality results in better voice output but less variety.-1 ≤ n ≤ 1 · nullable
reference_audio_base64stringReference audio to use for the voice generation. The audio should be base64 encoded. Only supported when using the eleven_ttv_v3 model.nullable
prompt_strengthnumberControls the balance of prompt versus reference audio when generating voice samples. 0 means almost no prompt influence, 1 means almost no reference audio influence. Only supported when using the eleven_ttv_v3 model.0 ≤ n ≤ 1 · nullable

Validate a payload

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