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
24K runs
$0.001 per second of audio
Commercial use

Iterate in playground

Run with an API

Playground API Examples README

Input

text

*string

Shift + Return to add a new line

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.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.

Text for speech generation

voice

string

Voice to use for generation

Default: "Angelo (Young male US conversational voice)"

voice_2

string

Optional second voice to use for generation

Default: "None"

language

string

The language of the text to be spoken.

Default: "english"

emotion

string

The emotion to use for the generated audio.

Default: "None"

temperature

number

(minimum: 0.1, maximum: 1.5)

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. Between 1.02 and 1.05 give good results.

Default: 1.02

prompt

string

Shift + Return to add a new line

A prompt to guide the style of the output generated by the first voice.

Default: ""

prompt2

string

Shift + Return to add a new line

A prompt to guide the style of the output generated by the second voice.

Default: ""

turnPrefix

string

Shift + Return to add a new line

The prefix to indicate the start of a turn in a multi-turn dialogue for the first voice.

Default: "Voice 1:"

turnPrefix2

string

Shift + Return to add a new line

The prefix to indicate the start of a turn in a multi-turn dialogue for the second voice.

Default: "Voice 2:"

voice_conditioning_seconds

integer

(minimum: 1, maximum: 60)

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.

Default: 20

voice_conditioning_seconds_2

integer

(minimum: 1, maximum: 60)

The number of seconds of conditioning to use from the second selected voice.

Default: 20

seed

integer

Random seed. Set for reproducible generation

Run this model in Node.js with one line of code:

npx create-replicate --model=playht/play-dialog

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

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: "",
  emotion: "None",
  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

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

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": "",
        "emotion": "None",
        "prompt2": "",
        "voice_2": "None",
        "language": "english",
        "turnPrefix": "Voice 1:",
        "temperature": 1.02,
        "turnPrefix2": "Voice 2:",
        "voice_conditioning_seconds": 20,
        "voice_conditioning_seconds_2": 20
    }
)
print(output)

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

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

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": "",
      "emotion": "None",
      "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 itReport

Pricing

Model pricing for playht/play-dialog. Looking for volume pricing? Get in touch.

$1.00

per thousand seconds of output audio

or around 1,000 seconds for $1

Official models are always on, maintained, and have predictable pricing. Learn more.

Check out our docs for more information about how pricing works on Replicate.

Readme

PlayDialog

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

Features

Core Speech Model

Context-aware speech generation using Adaptive Speech Contextualizer (ASC) architecture
Prosody and intonation control based on conversation history
Emotion-aware speech synthesis
Support for streaming responses from LLMs via WebSocket
Trained on hundreds of millions of real conversation samples
Complementary to Play 3.0 mini (which supports 30+ languages with low latency)

Performance

2:1 preference ratio in blind testing against leading competitors (n=600)
Strong performance in expressiveness metrics
Optimized for conversation flow and natural speech patterns

Support

For technical support or sales inquiries, contact our support team.