tmappdev/cosy_voice_cloner:a1bdb3a7 – Run with an API on Replicate

Version

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

tmappdev /cosy_voice_cloner:a1bdb3a7

Playground API

Input

ref_audio

*file

Reference audio file (3-10 seconds)

prompt_text

string

Shift + Return to add a new line

Text of the reference audio (optional)

Default: ""

prompt_language

string

Language of reference audio

Default: "粤语"

text

*string

Shift + Return to add a new line

Text to synthesize

text_language

string

Language of the text to synthesize

Default: "粤语"

how_to_cut

string

How to split text

Default: "按标点符号切"

top_k

integer

(minimum: 1, maximum: 100)

GPT top_k parameter

Default: 15

top_p

number

(minimum: 0, maximum: 1)

GPT top_p parameter

Default: 1

temperature

number

(minimum: 0, maximum: 1)

GPT temperature parameter

Default: 1

ref_free

boolean

Enable reference-free mode

Default: false

speed

number

(minimum: 0.6, maximum: 1.65)

Speech speed adjustment

Default: 1

reference_files

file[]

Add multiple files

Optional additional reference files to blend

Run this model in Node.js with one line of code:

npx create-replicate --model=tmappdev/cosy_voice_cloner

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run tmappdev/cosy_voice_cloner using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "tmappdev/cosy_voice_cloner:a1bdb3a77a40c876d8816c2aea7ec24f5c181b6461946f36f8d0e636d8446417",
  {
    input: {
      speed: 1,
      top_k: 15,
      top_p: 1,
      ref_free: false,
      how_to_cut: "按标点符号切",
      prompt_text: "",
      temperature: 1,
      text_language: "粤语",
      prompt_language: "粤语"
    }
  }
);

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run tmappdev/cosy_voice_cloner using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "tmappdev/cosy_voice_cloner:a1bdb3a77a40c876d8816c2aea7ec24f5c181b6461946f36f8d0e636d8446417",
    input={
        "speed": 1,
        "top_k": 15,
        "top_p": 1,
        "ref_free": False,
        "how_to_cut": "按标点符号切",
        "prompt_text": "",
        "temperature": 1,
        "text_language": "粤语",
        "prompt_language": "粤语"
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run tmappdev/cosy_voice_cloner using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "tmappdev/cosy_voice_cloner:a1bdb3a77a40c876d8816c2aea7ec24f5c181b6461946f36f8d0e636d8446417",
    "input": {
      "speed": 1,
      "top_k": 15,
      "top_p": 1,
      "ref_free": false,
      "how_to_cut": "按标点符号切",
      "prompt_text": "",
      "temperature": 1,
      "text_language": "粤语",
      "prompt_language": "粤语"
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

No output yet! Press "Submit" to start a prediction.