elevenlabs / elevenlabs-python

The official Python API for ElevenLabs Text to Speech.
https://elevenlabs.io/docs/api-reference/getting-started
MIT License
2.2k stars 255 forks source link

Voice cloning return wrong voice #343

Open GUIZ4RD opened 3 months ago

GUIZ4RD commented 3 months ago

Hi, I cloned my voice using 10 minutes of studio-recorded audio and the following code on colab:

TEXT = <SOME ITALIAN TEXT TO SPEAK>

client = ElevenLabs(
    api_key="<MY API KEY>",
)

voice = client.clone(
    name="Giuseppe",
    files=audio_files,
    description="an italian man who speaks Italian. Friendly voice, perfect for technical courses.",
)

audio = client.generate(text=TEXT, voice=voice)
play(audio, notebook=True)

When I generate audio through the website, the result is excellent. However, when I generate it using the API, the voice sounds different from mine and has an English accent. I've tried using the same text and same voice settings in both cases, but the issue persists.

Here’s what I’ve tried so far:

None of this worked, I keep getting a wrong voice.