cinemasetfree.com
← Back to all generators
playht/play-dialog
OfficialView on Replicate →
End-to-end AI speech model designed for natural-sounding conversational speech synthesis, with support for context-aware prosody, intonation, and emotional expression.
Capabilities
Seed
Cost
Community model (estimated from hardware time)
Input Parameters
| Name | Type | Description | Default | Constraints |
|---|---|---|---|---|
text* | string | Text for speech generation | — | — |
language | string | The language of the text to be spoken. | "english" | afrikaansalbanianamharicarabicbengalibulgariancatalancroatianczechdanishdutchenglishfrenchgaliciangermangreekhebrewhindihungarianindonesianitalianjapanesekoreanmalaymandarinpolishportugueserussianserbianspanishswedishtagalogthaiturkishukrainianurduxhosa |
prompt | string | A prompt to guide the style of the output generated by the first voice. | "" | — |
prompt2 | string | A prompt to guide the style of the output generated by the second voice. | "" | — |
seed | integer | Random seed. Set for reproducible generation | — | — |
speed | number | Control how fast the generated audio should be. | 1 | min: 0.1, max: 5 |
temperature | number | The temperature parameter controls variance. Lower temperatures result in more predictable results, higher temperatures allow each run to vary more, so the voice may sound less like the baseline voice. | 1 | min: 0, max: 2 |
turnPrefix | string | The prefix to indicate the start of a turn in a multi-turn dialogue for the first voice. | "Voice 1:" | — |
turnPrefix2 | string | The prefix to indicate the start of a turn in a multi-turn dialogue for the second voice. | "Voice 2:" | — |
voice | string | Voice to use for generation | "Angelo (Young male US conversational voice)" | Angelo (Young male US conversational voice)Arsenio (Middle-aged male US African American conversational voice)Cillian (Middle-aged male Irish conversational voice)Timo (Middle-aged male US conversational voice)Dexter (Middle-aged male US conversational voice)Miles (Young male US African American conversational voice)Briggs (Elderly male US Southern (Oklahoma) conversational voice)Deedee (Middle-aged female US African American conversational voice)Nia (Young female US conversational voice)Inara (Middle-aged female US African American conversational voice)Constanza (Young female US Latin American conversational voice)Gideon (Elderly male British narrative voice)Casper (Middle-aged male US narrative voice)Mitch (Middle-aged male Australian narrative voice)Ava (Middle-aged female Australian narrative voice) |
voice_2 | string | Optional second voice to use for generation | "None" | NoneAngelo (Young male US conversational voice)Arsenio (Middle-aged male US African American conversational voice)Cillian (Middle-aged male Irish conversational voice)Timo (Middle-aged male US conversational voice)Dexter (Middle-aged male US conversational voice)Miles (Young male US African American conversational voice)Briggs (Elderly male US Southern (Oklahoma) conversational voice)Deedee (Middle-aged female US African American conversational voice)Nia (Young female US conversational voice)Inara (Middle-aged female US African American conversational voice)Constanza (Young female US Latin American conversational voice)Gideon (Elderly male British narrative voice)Casper (Middle-aged male US narrative voice)Mitch (Middle-aged male Australian narrative voice)Ava (Middle-aged female Australian narrative voice) |
voice_conditioning_seconds | integer | The number of seconds of conditioning to use from the selected voice. Lower values generate audio less similar to the cloned voice, but lead to more model stability and expressiveness. Higher values create output more similar to the cloned voice, but can lead to model instability and reduced expressiveness. | 20 | min: 1, max: 60 |
voice_conditioning_seconds_2 | integer | The number of seconds of conditioning to use from the second selected voice. | 20 | min: 1, max: 60 |
textrequiredstringText for speech generation
languagestringThe language of the text to be spoken.
Default:
"english"afrikaansalbanianamharicarabicbengalibulgariancatalancroatianczechdanishdutchenglishfrenchgaliciangermangreekhebrewhindihungarianindonesianitalianjapanesekoreanmalaymandarinpolishportugueserussianserbianspanishswedishtagalogthaiturkishukrainianurduxhosa
promptstringA prompt to guide the style of the output generated by the first voice.
Default:
""prompt2stringA prompt to guide the style of the output generated by the second voice.
Default:
""seedintegerRandom seed. Set for reproducible generation
speednumberControl how fast the generated audio should be.
Default:
1min: 0.1, max: 5temperaturenumberThe temperature parameter controls variance. Lower temperatures result in more predictable results, higher temperatures allow each run to vary more, so the voice may sound less like the baseline voice.
Default:
1min: 0, max: 2turnPrefixstringThe prefix to indicate the start of a turn in a multi-turn dialogue for the first voice.
Default:
"Voice 1:"turnPrefix2stringThe prefix to indicate the start of a turn in a multi-turn dialogue for the second voice.
Default:
"Voice 2:"voicestringVoice to use for generation
Default:
"Angelo (Young male US conversational voice)"Angelo (Young male US conversational voice)Arsenio (Middle-aged male US African American conversational voice)Cillian (Middle-aged male Irish conversational voice)Timo (Middle-aged male US conversational voice)Dexter (Middle-aged male US conversational voice)Miles (Young male US African American conversational voice)Briggs (Elderly male US Southern (Oklahoma) conversational voice)Deedee (Middle-aged female US African American conversational voice)Nia (Young female US conversational voice)Inara (Middle-aged female US African American conversational voice)Constanza (Young female US Latin American conversational voice)Gideon (Elderly male British narrative voice)Casper (Middle-aged male US narrative voice)Mitch (Middle-aged male Australian narrative voice)Ava (Middle-aged female Australian narrative voice)
voice_2stringOptional second voice to use for generation
Default:
"None"NoneAngelo (Young male US conversational voice)Arsenio (Middle-aged male US African American conversational voice)Cillian (Middle-aged male Irish conversational voice)Timo (Middle-aged male US conversational voice)Dexter (Middle-aged male US conversational voice)Miles (Young male US African American conversational voice)Briggs (Elderly male US Southern (Oklahoma) conversational voice)Deedee (Middle-aged female US African American conversational voice)Nia (Young female US conversational voice)Inara (Middle-aged female US African American conversational voice)Constanza (Young female US Latin American conversational voice)Gideon (Elderly male British narrative voice)Casper (Middle-aged male US narrative voice)Mitch (Middle-aged male Australian narrative voice)Ava (Middle-aged female Australian narrative voice)
voice_conditioning_secondsintegerThe number of seconds of conditioning to use from the selected voice. Lower values generate audio less similar to the cloned voice, but lead to more model stability and expressiveness. Higher values create output more similar to the cloned voice, but can lead to model instability and reduced expressiveness.
Default:
20min: 1, max: 60voice_conditioning_seconds_2integerThe number of seconds of conditioning to use from the second selected voice.
Default:
20min: 1, max: 60Version:
0d5710136b22Updated: 7/25/202627.1K runs