Fish Audio Voice Cloning
Audio
Fish Audio Voice Cloning
POST
Fish Audio Voice Cloning
Fish Audio API for creating a voice model (voice cloning).Documentation Index
Fetch the complete documentation index at: https://novita.ai/docs/llms.txt
Use this file to discover all available pages before exploring further.
Request Headers
Enum:
application/jsonBearer authentication format, for example: Bearer {{API Key}}.
Request Body
Model type, tts is for text to speech.Available options:
ttsAllowed value: "tts"Model title or name.
Model train mode, for TTS model, fast means model instantly available after creation.Available options:
fastAllowed value: "fast"Upload voices files that will be used to tune the model.
Model visibility, public will be shown in the discovery page, unlist allows anyone with the link to access, private only be visible to the creator.Available options:
public, unlist, privateModel description.
Model cover image, this is required if the model is public.
Texts corresponding to the voices, if unspecified, ASR will be performed on the voices.
Model tags.
Enhance audio quality.
Response
Unique identifier for the created model.
Model type.Available options:
svc, ttsModel title or name.
Model description.
URL of the model cover image.
Current state of the model.Available options:
created, training, trained, failedModel tags.
Timestamp when the model was created.
Timestamp when the model was last updated.
Model visibility setting.Available options:
public, unlist, privateNumber of likes the model has received.
Number of marks/bookmarks the model has received.
Number of times the model has been shared.
Number of tasks associated with the model.
Information about the model author.
Training mode used for the model.Available options:
fast, fullSample data associated with the model.
Languages supported by the model.
Whether the visibility setting is locked.
Whether the current user has unliked the model.
Whether the current user has liked the model.
Whether the current user has marked/bookmarked the model.