Synthesize voice audio
Required scope: voice:manage
Generates speech from text with ElevenLabs or OpenAI and stores it as an audio asset. Without credentialId Polymorfa’s provider key is used; with it, your stored key for that provider. The provider processes the text. The asset converts asynchronously like an upload.
Authorizations
Send your team API key or project token as Authorization: Bearer <token>. The credential must have the required permissions. Project tokens can access only their own project.
Body
Human-readable name for this resource.
Value constraints
1 - 100Text to speak: up to 5,000 characters for ElevenLabs and 4,096 for OpenAI.
Value constraints
1 - 5000Specifies provider for this management platform access synthesize voice audio request.
Allowed values
elevenlabs, openai ElevenLabs voice ID, or an OpenAI voice name such as alloy.
Value constraints
1 - 64Project that owns the asset. Required for organization keys.
Value constraints
ElevenLabs: eleven_multilingual_v2 (default), eleven_flash_v2_5, eleven_turbo_v2_5. OpenAI: gpt-4o-mini-tts (default), tts-1, tts-1-hd.
Value constraints
1 - 64Use your stored key for the provider. Omit to use Polymorfa's key.
Value constraints
Specifies retention days for this management platform access synthesize voice audio request.
Value constraints
1 <= x <= 3650