chenxwh/openvoice 📝🖼️🔢❓ → 🖼️

▶️ 77.0K runs 📅 Jan 2024 ⚙️ Cog v0.9.6+dev 🔗 GitHub 📄 Paper ⚖️ License
multilingual-tts speech-style-transfer text-to-speech voice-cloning

About

Updated to OpenVoice v2: Versatile Instant Voice Cloning

Example Output

Output

Example output

Performance Metrics

5.78s Prediction Time
5.84s Total Time
All Input Parameters 
{
  "text": "Did you ever hear a folk tale about a giant turtle?",
  "audio": "https://replicate.delivery/pbxt/KpK4hkLwhVAJE9K0DAbZP3YfwLzJyLl09kuPnc4MvCYLcX8m/example_reference.mp3",
  "speed": 1,
  "language": "EN_NEWEST"
}
Input Parameters
text Type: stringDefault: Did you ever hear a folk tale about a giant turtle?
Input text
audio (required) Type: string
Input reference audio
speed Type: numberDefault: 1
Set speed scale of the output audio
language Default: EN_NEWEST
The language of the audio to be generated
Output Schema

Output

Type: string • Format: uri

Example Execution Logs 
OpenVoice version: v2
> Text split to sentences.
Did you ever hear a folk tale about a giant turtle?
> ===========================
  0%|          | 0/1 [00:00<?, ?it/s]
100%|██████████| 1/1 [00:00<00:00, 15.59it/s]
Version Details
Version ID
d548923c9d7fc9330a3b7c7f9e2f91b2ee90c83311a351dfcd32af353799223d
Version Created
May 18, 2024
Run on Replicate →