Generate > Text to Speech

Text to Speech

Create speech audio from text and a reusable voice asset.

POST/api/app/v1/generate/audio

Examples

curl -X POST https://medux-server-api-dev.lingverse.co/api/app/v1/generate/audio \
  -H 'Authorization: Bearer $MEDUX_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"links":["https://example.com/reference"],"model":"MODEL","model_id":"MODEL_ID","text":"Hello from Medux","title":"Demo title","voice_asset_id":"VOICE_ASSET_ID"}'

Media Samples

Approved examples for understanding request inputs, response shape, and official example output.

Official text-to-speech audio

This example uses speech-standard.

Sample request

Generate speech audio from text with an official public voice.

voice_asset_idofficial_voice_demo_001textWelcome to Medux. This audio was generated from text.model_idspeech-standardmodel_idspeech-standard

Sample response

Official example output for preview only. It is not a user Media Result.

output_urlOfficial example audio output

Example output

Auth Requirements

Authentication is required via Authorization header.

Preconditions

Requires a voice_asset_id.

Requires voice_asset_id from your Media Assets or official public assets, plus non-empty text.

Also accepts optional links and model.

Request

Body

application/json

Authorizationstringrequired

Bearer token or API key.

Location: HEADER

linksarray<string>optional

Optional reference links collected from the Playground form.

Location: BODY

modelstringoptional

Selected generation model label or version from the Playground form.

Location: BODY

model_idstringoptional

Stable public Medux model identifier.

Location: BODY

textstringoptional

No description provided.

Location: BODY

titlestringoptional

No description provided.

Location: BODY

voice_asset_idstringrequired

Reusable voice asset ID owned by the current user or listed as an official public asset.

Location: BODY

Response

application/json

codeint32optional

response code enums:
.. 0: ok
.. 12: invalid input
.. 1410: invalid model
.. 1409: paid plan required
.. 1401: insufficient credits
.... 1401 ~ 1499 是 media
.. 1402: asset category mismatch
.. 1403: voice asset required
.. 1407: asset locked
.. 1408: asset expired
.. 1404: provider error
.. 1405: provider timeout
.. 13: unauthenticated
.. 16: rate limit
.. 99: server error

Available options: 0 12 1410 1409 1401 1402 1403 1407 1408 1404 1405 13 16 99

Location: RESPONSE

data.assetobjectoptional

No description provided.

Location: RESPONSE

data.paid_plan_requiredobjectoptional

No description provided.

Location: RESPONSE

data.taskobjectoptional

No description provided.

Location: RESPONSE

messagestringoptional

No description provided.

Available options: ok invalid input invalid model paid plan required insufficient credits asset category mismatch voice asset required asset locked asset expired provider error provider timeout unauthenticated rate limit server error

Location: RESPONSE

MCP Tool

This endpoint is also available through the Medux-hosted remote MCP service.

Speech / Text-to-Speech Audio

Create speech audio from text and an optional reusable voice asset.

Invocation Example

Generate speech audio from this text using voice_asset_id {voice_asset_id} and model_id speech-standard.

medux_speech_create_audioResult: audio

voice_asset_id{voice_asset_id}text{text}model_idspeech-standard

On this page