Voice Clone

"""
Example for obtaining the file_id of the source audio.
Note: Make sure your API key is set in the environment variable `MINIMAX_API_KEY`.
"""
import requests
import os

api_key = os.getenv("MINIMAX_API_KEY")
url = "https://api.minimax.io/v1/files/upload"

payload = {"purpose": "voice_clone"}
files = [
  ("file", ("clone_input.mp3", open("/Users/minimax/Downloads/clone_input.mp3", "rb")))
]
headers = {"Authorization": f"Bearer {api_key}"}

response = requests.post(url, headers=headers, data=payload, files=files)
response.raise_for_status()
file_id = response.json().get("file", {}).get("file_id")
print(file_id)

"""
Example for obtaining the file_id of the example audio.
Note: Ensure `MINIMAX_API_KEY` is set.
"""
import requests
import os

api_key = os.getenv("MINIMAX_API_KEY")
url = "https://api.minimax.io/v1/files/upload"

payload = {"purpose": "prompt_audio"}
files = [
  ("file", ("clone_prompt.mp3", open("/Users/minimax/Downloads/clone_prompt.mp3", "rb")))
]
headers = {"Authorization": f"Bearer {api_key}"}

response = requests.post(url, headers=headers, data=payload, files=files)
response.raise_for_status()
prompt_file_id = response.json().get("file", {}).get("file_id")
print(prompt_file_id)

"""
Example for voice cloning.
Note: Set `MINIMAX_API_KEY` in environment variables,
and replace "<voice_id>", <file_id_of_cloned_voice>, <file_id_of_prompt_audio> with actual values.
"""
import requests
import os

api_key = os.getenv("MINIMAX_API_KEY")
url = "https://api.minimax.io/v1/voice_clone"

payload = {
    "file_id": <file_id_of_cloned_voice>,
    "voice_id": "<your_custom_voice_id>",
    "clone_prompt": {
        "prompt_audio": <file_id_of_prompt_audio>,
        "prompt_text": "This voice sounds natural and pleasant."
    },
    "text": "A gentle breeze passes over the soft grass, accompanied by the fresh scent and birdsong.",
    "model": "speech-2.5-hd-preview"
}

headers = {
    "Authorization": f"Bearer {api_key}",
    "Content-Type": "application/json"
}

response = requests.post(url, headers=headers, json=payload)
response.raise_for_status()
print(response.text)

"""
Example demonstrating full voice cloning workflow and obtaining preview audio.
Note: Set `MINIMAX_API_KEY` in environment variables,
and replace "<your_custom_voice_id>" with your defined voice ID.
"""
import requests
import os

api_key = os.getenv("MINIMAX_API_KEY")
upload_url = "https://api.minimax.io/v1/files/upload"
clone_url = "https://api.minimax.io/v1/voice_clone"
headers = {"Authorization": f"Bearer {api_key}"}

# 1. Upload source audio
with open("/path/to/clone_input.mp3", "rb") as f:
    files = {"file": ("clone_input.mp3", f)}
    data = {"purpose": "voice_clone"}
    response = requests.post(upload_url, headers=headers, data=data, files=files)
    file_id = response.json()["file"]["file_id"]
    print(f"File ID of the cloned audio: {file_id}")

# 2. Upload example audio
with open("/path/to/clone_prompt.mp3", "rb") as f:
    files = {"file": ("clone_prompt.mp3", f)}
    data = {"purpose": "prompt_audio"}
    response = requests.post(upload_url, headers=headers, data=data, files=files)
    prompt_file_id = response.json()["file"]["file_id"]
    print(f"File ID of the prompt audio: {prompt_file_id}")

# 3. Clone the voice
clone_payload = {
    "file_id": file_id,
    "voice_id": "<your_custom_voice_id>",
    "clone_prompt": {
        "prompt_audio": prompt_file_id,
        "prompt_text": "This is a child's voice to be used for cloning."
    },
    "text": "A gentle breeze passes over the soft grass, accompanied by the fresh scent and birdsong.",
    "model": "speech-2.5-hd-preview"
}
clone_headers = {
    "Authorization": f"Bearer {api_key}",
    "Content-Type": "application/json"
}
response = requests.post(clone_url, headers=clone_headers, json=clone_payload)
print(response.text)