sepal/audiogen 🔢📝❓ → 🖼️

▶️ 85.5K runs 📅 Aug 2023 ⚙️ Cog 0.8.3 🔗 GitHub 📄 Paper ⚖️ License
sound-effect-generation text-to-audio

About

Generate sounds from a text prompt

Example Output

Prompt:

"Formula f1 cars driving by"

Output

Example output

Performance Metrics

13.60s Prediction Time
452.06s Total Time
All Input Parameters 
{
  "top_k": 250,
  "top_p": 0,
  "prompt": "Formula f1 cars driving by",
  "duration": 5,
  "temperature": 1,
  "output_format": "mp3",
  "classifier_free_guidance": 3
}
Input Parameters
top_k Type: integerDefault: 250
Reduces sampling to the k most likely tokens.
top_p Type: numberDefault: 0
Reduces sampling to tokens with cumulative probability of p. When set to `0` (default), top_k sampling is used.
prompt (required) Type: string
Prompt that describes the sound
duration Type: numberDefault: 3Range: 1 - 10
Max duration of the sound
temperature Type: numberDefault: 1
Controls the 'conservativeness' of the sampling process. Higher temperature means more diversity.
output_format Default: wav
Output format for generated audio.
classifier_free_guidance Type: integerDefault: 3
Increases the influence of inputs on the output. Higher values produce lower-varience outputs that adhere more closely to inputs.
Output Schema

Output

Type: string • Format: uri

Version Details
Version ID
154b3e5141493cb1b8cec976d9aa90f2b691137e39ad906d2421b74c2a8c52b8
Version Created
August 21, 2023
Run on Replicate →