declare-lab/tango ❓🔢📝 → 🖼️

▶️ 128.3K runs 📅 Jun 2023 ⚙️ Cog v0.9.6+dev 🔗 GitHub 📄 Paper ⚖️ License
sound-effect-generation text-to-audio

About

Tango 2: Use text prompts to make sound effects

Example Output

Prompt:

"Quiet speech and then and airplane flying away"

Output

Example output

Performance Metrics

12.39s Prediction Time
184.05s Total Time
All Input Parameters 
{
  "model": "tango2",
  "steps": 100,
  "prompt": "Quiet speech and then and airplane flying away",
  "guidance": 3
}
Input Parameters
model Default: tango2
choose a model
steps Type: integerDefault: 100
inference steps
prompt Type: stringDefault: Quiet speech and then and airplane flying away
Input prompt
guidance Type: numberDefault: 3
guidance scale
Output Schema

Output

Type: string • Format: uri

Version Details
Version ID
740e4f5e59bd3b871c9e5b4efbff7ded516d40aa6abf4e95fd5e8dd149b7bc3f
Version Created
May 1, 2024
Run on Replicate →