Kurzanleitung für professionelles Voice Cloning

# example.py
import os
import time
import base64
from contextlib import ExitStack
from io import BytesIO
from dotenv import load_dotenv
from elevenlabs.client import ElevenLabs
load_dotenv()
elevenlabs = ElevenLabs(
  api_key=os.getenv("ELEVENLABS_API_KEY"),
)
voice = elevenlabs.voices.pvc.create(
    name="My Professional Voice Clone",
    language="en",
    description="A professional voice clone of my voice"
)
print(voice)

# Define the list of file paths explicitly
# Replace with the paths to your audio and/or video files.
# The more files you add, the better the clone will be.
sample_file_paths = [
    "/path/to/your/first_sample.mp3",
    "/path/to/your/second_sample.wav",
    "relative/path/to/another_sample.mp4"
]
samples = None
files_to_upload = []
# Use ExitStack to manage multiple open files
with ExitStack() as stack:
    for filepath in sample_file_paths:
        # Open each file and add it to the stack
        audio_file = stack.enter_context(open(filepath, "rb"))
        filename = os.path.basename(filepath)
        # Create a File object for the SDK
        files_to_upload.append(
            BytesIO(audio_file.read())
        )
    samples = elevenlabs.voices.pvc.samples.create(
        voice_id=voice.voice_id,
        files=files_to_upload # Pass the list of File objects
    )

sample_ids_to_check = []
for sample in samples:
    if sample.sample_id:
        print(f"Starting separation for sample: {sample.sample_id}")
        elevenlabs.voices.pvc.samples.speakers.separate(
            voice_id=voice.voice_id,
            sample_id=sample.sample_id
        )
        sample_ids_to_check.append(sample.sample_id)
while sample_ids_to_check:
    # Create a copy of the list to iterate over, so we can remove items from the original
    ids_in_batch = list(sample_ids_to_check)
    for sample_id in ids_in_batch:
        status_response = elevenlabs.voices.pvc.samples.speakers.get(
            voice_id=voice.voice_id,
            sample_id=sample_id
        )
        status = status_response.status
        print(f"Sample {sample_id} status: {status}")
        if status == "completed" or status == "failed":
            sample_ids_to_check.remove(sample_id)
    if sample_ids_to_check:
        # Wait before the next poll cycle
        time.sleep(5) # Wait for 5 seconds
print("All samples have been processed or removed from polling.")

# Get the list of samples from the voice created in Step 3
voice = elevenlabs.voices.get(voice_id=voice_id)
samples = voice.samples
# Loop over each sample and save the audio for each speaker to a file
speaker_audio_output_dir = "path/to/speakers/"
if not os.path.exists(speaker_audio_output_dir):
    os.makedirs(speaker_audio_output_dir)
for sample in samples:
    speaker_info = elevenlabs.voices.pvc.samples.speakers.get(
        voice_id=voice.voice_id,
        sample_id=sample.sample_id
    )
    # Proceed only if separation is actually complete
    if getattr(speaker_info, 'status', 'unknown') != "completed":
        continue
    if hasattr(speaker_info, 'speakers') and speaker_info.speakers:
        speaker_list = speaker_info.speakers
        if isinstance(speaker_info.speakers, dict):
            speaker_list = speaker_info.speakers.values()
        for speaker in speaker_list:
            audio_response = elevenlabs.voices.pvc.samples.speakers.audio.get(
                voice_id=voice.voice_id,
                sample_id=sample.sample_id,
                speaker_id=speaker.speaker_id
            )
            audio_base64 = audio_response.audio_base_64
            audio_data = base64.b64decode(audio_base64)
            output_filename = os.path.join(speaker_audio_output_dir, f"sample_{sample.sample_id}_speaker_{speaker.speaker_id}.mp3")
            with open(output_filename, "wb") as f:
                f.write(audio_data)

elevenlabs.voices.pvc.samples.update(
    voice_id=voice.voice_id,
    sample_id=sample.sample_id,
    selected_speaker_ids=[speaker.speaker_id]
)

captcha_response = elevenlabs.voices.pvc.verification.captcha.get(voice.voice_id)
# Save captcha image to file
captcha_buffer = base64.b64decode(captcha_response)
with open('captcha.png', 'wb') as f:
    f.write(captcha_buffer)

elevenlabs.voices.pvc.verification.captcha.verify(
    voice_id=voice.voice_id,
    recording=open('path/to/recording.mp3', 'rb')
)

elevenlabs.voices.pvc.verification.request(
    voice_id=voice.voice_id,
    files=[open('path/to/verification/files.txt', 'rb')],
)

elevenlabs.voices.pvc.train(
    voice_id=voice.voice_id,
    # Specify the model the PVC should be trained on
    model_id="eleven_multilingual_v2"
)
# Poll the fine tuning status until it is complete or fails
# This example specifically checks for the eleven_multilingual_v2 model
while True:
    voice_details = elevenlabs.voices.get(voice_id=voice.voice_id)
    fine_tuning_state = None
    if voice_details.fine_tuning and voice_details.fine_tuning.state:
        fine_tuning_state = voice_details.fine_tuning.state.get("eleven_multilingual_v2")
    if fine_tuning_state:
        progress = None
        if voice_details.fine_tuning.progress and voice_details.fine_tuning.progress.get("eleven_multilingual_v2"):
            progress = voice_details.fine_tuning.progress.get("eleven_multilingual_v2")
        print(f"Fine tuning progress: {progress}")
        if fine_tuning_state == "fine_tuned" or fine_tuning_state == "failed":
            print("Fine tuning completed or failed")
            break
    # Wait for 5 seconds before polling again
    time.sleep(5)