playht / play-dialog

End-to-end AI speech model designed for natural-sounding conversational speech synthesis, with support for context-aware prosody, intonation, and emotional expression.

Warm

Public
26.4K runs
$1 per thousand seconds of output audio
Commercial use

Iterate in playground

Run with an API

Playground API Examples README

Prediction

playht/play-dialog

Official model

playht/play-dialog

5rg3tz0yesrgc0cme4wbb11hqw

Status

Succeeded

Source

Web

Total duration

26.5s

Created

6 months ago

Input

text: Close your eyes gently. Take a deep breath in through your nose, allowing your lungs to fill completely. Hold it for a moment, then exhale slowly and deeply through your mouth. Let any tension you're holding melt away with each exhale. Visualize yourself standing at the edge of a beautiful, tranquil forest. The first rays of morning light stream through the trees, illuminating the delicate dewdrops on leaves and petals. Birds are beginning to sing their morning songs, and the world feels fresh and alive.
voice: Nia (Young female US conversational voice)
prompt
prompt2
voice_2: None
language: english
turnPrefix: Voice 1:
temperature: 1.02
turnPrefix2: Voice 2:
voice_conditioning_seconds: 20
voice_conditioning_seconds_2: 20

{
  "text": "Close your eyes gently. Take a deep breath in through your nose, allowing your lungs to fill completely. Hold it for a moment, then exhale slowly and deeply through your mouth. Let any tension you're holding melt away with each exhale. Visualize yourself standing at the edge of a beautiful, tranquil forest. The first rays of morning light stream through the trees, illuminating the delicate dewdrops on leaves and petals. Birds are beginning to sing their morning songs, and the world feels fresh and alive.",
  "voice": "Nia (Young female US conversational voice)",
  "prompt": "",
  "prompt2": "",
  "voice_2": "None",
  "language": "english",
  "turnPrefix": "Voice 1:",
  "temperature": 1.02,
  "turnPrefix2": "Voice 2:",
  "voice_conditioning_seconds": 20,
  "voice_conditioning_seconds_2": 20
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run playht/play-dialog using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const input = {
  text: "Close your eyes gently. Take a deep breath in through your nose, allowing your lungs to fill completely. Hold it for a moment, then exhale slowly and deeply through your mouth. Let any tension you're holding melt away with each exhale. Visualize yourself standing at the edge of a beautiful, tranquil forest. The first rays of morning light stream through the trees, illuminating the delicate dewdrops on leaves and petals. Birds are beginning to sing their morning songs, and the world feels fresh and alive.",
  voice: "Nia (Young female US conversational voice)",
  prompt: "",
  prompt2: "",
  voice_2: "None",
  language: "english",
  turnPrefix: "Voice 1:",
  temperature: 1.02,
  turnPrefix2: "Voice 2:",
  voice_conditioning_seconds: 20,
  voice_conditioning_seconds_2: 20
};

const output = await replicate.run("playht/play-dialog", { input });

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run playht/play-dialog using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "playht/play-dialog",
    input={
        "text": "Close your eyes gently. Take a deep breath in through your nose, allowing your lungs to fill completely. Hold it for a moment, then exhale slowly and deeply through your mouth. Let any tension you're holding melt away with each exhale. Visualize yourself standing at the edge of a beautiful, tranquil forest. The first rays of morning light stream through the trees, illuminating the delicate dewdrops on leaves and petals. Birds are beginning to sing their morning songs, and the world feels fresh and alive.",
        "voice": "Nia (Young female US conversational voice)",
        "prompt": "",
        "prompt2": "",
        "voice_2": "None",
        "language": "english",
        "turnPrefix": "Voice 1:",
        "temperature": 1.02,
        "turnPrefix2": "Voice 2:",
        "voice_conditioning_seconds": 20,
        "voice_conditioning_seconds_2": 20
    }
)

# To access the file URL:
print(output.url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output.read())

To learn more, take a look at the guide on getting started with Python.

Run playht/play-dialog using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "input": {
      "text": "Close your eyes gently. Take a deep breath in through your nose, allowing your lungs to fill completely. Hold it for a moment, then exhale slowly and deeply through your mouth. Let any tension you\'re holding melt away with each exhale. Visualize yourself standing at the edge of a beautiful, tranquil forest. The first rays of morning light stream through the trees, illuminating the delicate dewdrops on leaves and petals. Birds are beginning to sing their morning songs, and the world feels fresh and alive.",
      "voice": "Nia (Young female US conversational voice)",
      "prompt": "",
      "prompt2": "",
      "voice_2": "None",
      "language": "english",
      "turnPrefix": "Voice 1:",
      "temperature": 1.02,
      "turnPrefix2": "Voice 2:",
      "voice_conditioning_seconds": 20,
      "voice_conditioning_seconds_2": 20
    }
  }' \
  https://api.replicate.com/v1/models/playht/play-dialog/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

Video Player is loading.

Current Time 00:00:000

Duration 00:00:000

Loaded: 0%

Stream Type LIVE

Remaining Time 00:00:000

{
  "completed_at": "2025-01-16T22:25:17.277017Z",
  "created_at": "2025-01-16T22:24:50.806000Z",
  "data_removed": false,
  "error": null,
  "id": "5rg3tz0yesrgc0cme4wbb11hqw",
  "input": {
    "text": "Close your eyes gently. Take a deep breath in through your nose, allowing your lungs to fill completely. Hold it for a moment, then exhale slowly and deeply through your mouth. Let any tension you're holding melt away with each exhale. Visualize yourself standing at the edge of a beautiful, tranquil forest. The first rays of morning light stream through the trees, illuminating the delicate dewdrops on leaves and petals. Birds are beginning to sing their morning songs, and the world feels fresh and alive.",
    "voice": "Nia (Young female US conversational voice)",
    "prompt": "",
    "prompt2": "",
    "voice_2": "None",
    "language": "english",
    "turnPrefix": "Voice 1:",
    "temperature": 1.02,
    "turnPrefix2": "Voice 2:",
    "voice_conditioning_seconds": 20,
    "voice_conditioning_seconds_2": 20
  },
  "logs": "Using seed: 1958393623\nRunning prediction... \nGenerating audio...\nStill processing...\nStill processing...\nStill processing...\nStill processing...\nStill processing...\nStill processing...\nStill processing...\nStill processing...\nStill processing...\nStill processing...\nStill processing...\nStill processing...\nStill processing...\nStill processing...\nStill processing...\nStill processing...\nStill processing...\nStill processing...\nStill processing...\nStill processing...\nStill processing...\nStill processing...\nGenerated audio in 26.1sec\nLength of generated audio: 39.24 seconds\nDownloading 785805 bytes\nDownloaded 0.75MB in 0.28sec",
  "metrics": {
    "predict_time": 26.463996378,
    "total_time": 26.471017
  },
  "output": "https://replicate.delivery/czjl/bIuSZOcpI4p6NtvHiEa9us7Zd272Jsl5ZhMk9tneHvmmy5CKA/tmpbuleb_9n.mp3",
  "started_at": "2025-01-16T22:24:50.813021Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/fddq-tzgxykagkckc3pqh4iioj5mfzclcvgdhghnrl4hv3snuppfbq2ua",
    "get": "https://api.replicate.com/v1/predictions/5rg3tz0yesrgc0cme4wbb11hqw",
    "cancel": "https://api.replicate.com/v1/predictions/5rg3tz0yesrgc0cme4wbb11hqw/cancel"
  },
  "version": "hidden"
}

Generated in

26.5 seconds

Tweak it ShareReport

Prediction

playht/play-dialog

Official model

playht/play-dialog

webf0ggcgsrg80cme698ajpqm4

Status

Succeeded

Source

Web

Total duration

16.5s

Created

6 months ago

Input

text: Voice 1: Why didn't you come home last night? I waited up for you for hours. Voice 2: I'm so sorry, I got caught up at work. You know how it gets sometimes. Voice 1: Don't lie to me, I saw your car outside that house! Voice 2: Please, let me explain! It's not what you think!
voice: Deedee (Middle-aged female US African American conversational voice)
prompt: Angry
prompt2: Guilty
voice_2: Angelo (Young male US conversational voice)
language: english
turnPrefix: Voice 1:
temperature: 1.02
turnPrefix2: Voice 2:
voice_conditioning_seconds: 20
voice_conditioning_seconds_2: 20

{
  "text": "Voice 1: Why didn't you come home last night? I waited up for you for hours.\nVoice 2: I'm so sorry, I got caught up at work. You know how it gets sometimes.\nVoice 1: Don't lie to me, I saw your car outside that house!\nVoice 2: Please, let me explain! It's not what you think!\n",
  "voice": "Deedee (Middle-aged female US African American conversational voice)",
  "prompt": "Angry",
  "prompt2": "Guilty",
  "voice_2": "Angelo (Young male US conversational voice)",
  "language": "english",
  "turnPrefix": "Voice 1:",
  "temperature": 1.02,
  "turnPrefix2": "Voice 2:",
  "voice_conditioning_seconds": 20,
  "voice_conditioning_seconds_2": 20
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run playht/play-dialog using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const input = {
  text: "Voice 1: Why didn't you come home last night? I waited up for you for hours.\nVoice 2: I'm so sorry, I got caught up at work. You know how it gets sometimes.\nVoice 1: Don't lie to me, I saw your car outside that house!\nVoice 2: Please, let me explain! It's not what you think!\n",
  voice: "Deedee (Middle-aged female US African American conversational voice)",
  prompt: "Angry",
  prompt2: "Guilty",
  voice_2: "Angelo (Young male US conversational voice)",
  language: "english",
  turnPrefix: "Voice 1:",
  temperature: 1.02,
  turnPrefix2: "Voice 2:",
  voice_conditioning_seconds: 20,
  voice_conditioning_seconds_2: 20
};

const output = await replicate.run("playht/play-dialog", { input });

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run playht/play-dialog using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "playht/play-dialog",
    input={
        "text": "Voice 1: Why didn't you come home last night? I waited up for you for hours.\nVoice 2: I'm so sorry, I got caught up at work. You know how it gets sometimes.\nVoice 1: Don't lie to me, I saw your car outside that house!\nVoice 2: Please, let me explain! It's not what you think!\n",
        "voice": "Deedee (Middle-aged female US African American conversational voice)",
        "prompt": "Angry",
        "prompt2": "Guilty",
        "voice_2": "Angelo (Young male US conversational voice)",
        "language": "english",
        "turnPrefix": "Voice 1:",
        "temperature": 1.02,
        "turnPrefix2": "Voice 2:",
        "voice_conditioning_seconds": 20,
        "voice_conditioning_seconds_2": 20
    }
)

# To access the file URL:
print(output.url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output.read())

To learn more, take a look at the guide on getting started with Python.

Run playht/play-dialog using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "input": {
      "text": "Voice 1: Why didn\'t you come home last night? I waited up for you for hours.\\nVoice 2: I\'m so sorry, I got caught up at work. You know how it gets sometimes.\\nVoice 1: Don\'t lie to me, I saw your car outside that house!\\nVoice 2: Please, let me explain! It\'s not what you think!\\n",
      "voice": "Deedee (Middle-aged female US African American conversational voice)",
      "prompt": "Angry",
      "prompt2": "Guilty",
      "voice_2": "Angelo (Young male US conversational voice)",
      "language": "english",
      "turnPrefix": "Voice 1:",
      "temperature": 1.02,
      "turnPrefix2": "Voice 2:",
      "voice_conditioning_seconds": 20,
      "voice_conditioning_seconds_2": 20
    }
  }' \
  https://api.replicate.com/v1/models/playht/play-dialog/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.