Pricing
For current pricing, see the Pricing page.Authentication
All endpoints require authentication using Bearer token authorization:Request
Parameters
Voice ID to use for speech generation (get from
/higgsfield/voices endpoint)Text to convert to speech
Background sound ID (get from
/higgsfield/sounds endpoint). If not provided, no background sound is usedDefault: "" (empty)Voice similarity boost (0-100). Higher values make the output more similar to the original voiceDefault:
90Voice style/expressiveness (0-100). Controls how expressive the voice isDefault:
60Speech speed (0-1.2). 1.0 is normal speed, lower is slower, higher is fasterDefault:
1.1Voice stability (0-100). Higher values make the voice more consistent/stableDefault:
30Important Notes
preset_nameparameter exists internally but is automatically set to matchsound_id. You don’t need to provide it
Response
Response Fields
HTTP status code (200 for success)
Error Responses
Parameter Out of Range:
Use the
task_id to check the status using the Get Task endpoint.