You're looking at a specific version of this model. Jump to the model overview.

jichengdu /cosyvoice:4106862b

Input schema

The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.

Field Type Default value Description
source_audio
string
Source audio / 源音频文件(参考来源)
source_transcript
string
Transcript of the source audio / 源音频(参考来源)的文字内容
tts_text
string
Text of the audio to generate / 要生成的音频文本内容
task
string (enum)
zero-shot voice clone

Options:

zero-shot voice clone, cross-lingual voice clone, Instructed Voice Generation

Task type / 任务类型:零样本声音克隆、跨语言声音克隆或指令式声音生成
instruction
string
Instruction for Instructed Voice Generation task / 指令式声音生成任务的指令内容

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{'format': 'uri', 'title': 'Output', 'type': 'string'}