lucataco/orpheus-3b-0.1-ft 📝🔢❓ → 🖼️

▶️ 29.4K runs 📅 Mar 2025 ⚙️ Cog 0.14.2 🔗 GitHub ⚖️ License
speech-synthesis text-to-speech

About

Orpheus 3B - high quality, emotive Text to Speech

Example Output

Output

Example output

Performance Metrics

9.56s Prediction Time
9.57s Total Time
All Input Parameters 
{
  "text": "Hey there my name is Tara, <chuckle> and I'm a speech generation model that can sound like a person.",
  "top_p": 0.95,
  "voice": "tara",
  "temperature": 0.6,
  "max_new_tokens": 1200,
  "repetition_penalty": 1.1
}
Input Parameters
text (required) Type: string
Text to convert to speech
top_p Type: numberDefault: 0.95Range: 0.1 - 1
Top P for nucleus sampling
voice Default: tara
Voice to use
temperature Type: numberDefault: 0.6Range: 0.1 - 1.5
Temperature for generation
max_new_tokens Type: integerDefault: 1200Range: 100 - 2000
Maximum number of tokens to generate
repetition_penalty Type: numberDefault: 1.1Range: 1 - 2
Repetition penalty
Output Schema

Output

Type: string • Format: uri

Example Execution Logs 
Setting `pad_token_id` to `eos_token_id`:128258 for open-end generation.
Version Details
Version ID
79f2a473e6a9720716a473d9b2f2951437dbf91dc02ccb7079fb3d89b881207f
Version Created
March 20, 2025
Run on Replicate →