• Supported service: tts
  • Key: playht
  • Integrated: No. See BYO Keys for more info.

Service options

user_id
string
required

Your PlayHT User ID, which can be found in your PlayHT account settings under API Access > User ID.

{
  "service_options": {
    "playht": {
      "user_id": "$YOUR_PLAYHT_USER_ID"
    }
  }
}
sample_rate
integer
default: "24000"

The audio output sample rate in Hz for the TTS audio.

The sample rate must be one of these values: 8000, 16000, 22050, 24000, 32000, 44100, 48000.

{
  "service_options": {
    "playht": {
      "sample_rate": 24000
    }
  }
}

Configuration options

model
string
default: "Play3.0-mini"

The model you want your TTS service to use. Select any of the available models found in the PlayHT library.

{
  "name": "model",
  "value": "Play3.0-mini"
}
voice
string
required

The voice you want your TTS service to use. Select any of the available voices found in the PlayHT library.

{
  "name": "voice",
  "value": "s3://voice-cloning-zero-shot/d82d246c-148b-457f-9668-37b789520891/adolfosaad/manifest.json"
}
language
string
default: "english"

The language you want your TTS service to use. Select any of the support PlayHT languages.

Note: non-English languages require a model of Play3.0-mini.

{
  "name": "language",
  "value": "spanish"
}
speed
float
default: "1.0"

Control how fast the generated audio should be. A number greater than 0 and less than or equal to 5.0

{
  "name": "speed",
  "value": 1.5
}
seed
integer
default: "None"

An integer number greater than or equal to 0. If equal to null or not provided, a random seed will be used. Useful to control the reproducibility of the generated audio. Assuming all other properties didn’t change, a fixed seed should always generate the exact same audio file.

{
  "name": "seed",
  "value": 42
}
text_filter
object

Control whether the TTS service filters out markdown, code blocks, or tables from its output.

Basic markdown filtering is enabled by default. Enable code and table filtering as needed. Filtering code and tables can help the TTS avoid mistakes.

{
  "name": "text_filter",
  "value": {
    "enable_text_filter": true,
    "filter_code": true,
    "filter_tables": true
  }
}