Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Voice cloning return wrong voice #343

Open
GUIZ4RD opened this issue Aug 14, 2024 · 0 comments
Open

Voice cloning return wrong voice #343

GUIZ4RD opened this issue Aug 14, 2024 · 0 comments

Comments

@GUIZ4RD
Copy link

GUIZ4RD commented Aug 14, 2024

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:

  • Cloning the voice through the website and then using it with the API, but I got the same result.
  • Creating a new API token twice.
  • Using the label {"language": "italian"} while cloning the voice.
  • Loading the voice using its ID.
  • Loading the voice getting it from the list returned by client.voices.get_all().

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

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant