← Back to all generators
lucataco/orpheus-3b-0.1-ft
OfficialView on Replicate →
Orpheus 3B - high quality, emotive Text to Speech
Capabilities
Max TokensTop-P
Cost
Community model (estimated from hardware time)
Input Parameters
| Name | Type | Description | Default | Constraints |
|---|---|---|---|---|
text* | string | Text to convert to speech | — | — |
max_new_tokens | integer | Maximum number of tokens to generate | 1200 | min: 100, max: 2000 |
repetition_penalty | number | Repetition penalty | 1.1 | min: 1, max: 2 |
temperature | number | Temperature for generation | 0.6 | min: 0.1, max: 1.5 |
top_p | number | Top P for nucleus sampling | 0.95 | min: 0.1, max: 1 |
voice | string | Voice to use | "tara" | taradanjoshemma |
textrequiredstringText to convert to speech
max_new_tokensintegerMaximum number of tokens to generate
Default:
1200min: 100, max: 2000repetition_penaltynumberRepetition penalty
Default:
1.1min: 1, max: 2temperaturenumberTemperature for generation
Default:
0.6min: 0.1, max: 1.5top_pnumberTop P for nucleus sampling
Default:
0.95min: 0.1, max: 1voicestringVoice to use
Default:
"tara"taradanjoshemma
Version:
79f2a473e6a9Updated: 8/12/202633.6K runs
cinemasetfree