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

Service options

region
string
required

Your Azure region.

{
  "service_options": {
    "azure_tts": {
      "region": "useast"
    }
  }
}
voice
string
default: "en-US-SaraNeural"

Initialize the voice for the TTS service. Select any voice from the available Azure TTS voices.

{
  "service_options": {
    "azure_tts": {
      "voice": "en-US-BrianNeural"
    }
  }
}
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, 44100, 48000.

{
  "service_options": {
    "azure_tts": {
      "sample_rate": 24000
    }
  }
}

Configuration options

voice
string
default: "en-US-SaraNeural"

The voice you want your TTS service to use. Select any voice from the available Azure TTS voices.

{
  "name": "voice",
  "value": "en-US-BrianNeural"
}
language
string
default: "en-US"

The language you the TTS service to use. Select any language from the available Azure TTS languages.

{
  "name": "language",
  "value": "es-MX"
}
pitch
string

The pitch of the voice. Learn more about using pitch with Azure here.

{
  "name": "pitch",
  "value": "medium"
}
rate
string

The pitch of the voice. Learn more about using pitch with Azure here.

{
  "name": "rate",
  "value": "medium"
}
volume
string

The pitch of the voice. Learn more about using pitch with Azure here.

{
  "name": "volume",
  "value": "loud"
}
role
string

The speaking role-play. The voice can imitate a different age and gender, but the voice name isn’t changed. Learn more.

Note: role is dependent on the voice you select.

{
  "name": "voice",
  "value": "zh-CN-XiaomoNeural"
},
{
  "name": "role",
  "value": "OlderAdultFemale"
}
style
string

The speaking role-play. The voice can imitate a different age and gender, but the voice name isn’t changed. Learn more.

Note: style is dependent on the voice you select.

{
  "name": "voice",
  "value": "en-US-AriaNeural"
},
{
  "name": "style",
  "value": "cheerful"
}
style_degree
string

The speaking role-play. The voice can imitate a different age and gender, but the voice name isn’t changed. Learn more.

Note: style_degree is dependent on the voice and style you select.

{
  "name": "voice",
  "value": "en-US-AriaNeural"
},
{
  "name": "style",
  "value": "cheerful"
},
{
  "name": "style_degree",
  "value": "1.2"
}
emphasis
string

Adjust the emphasis for the voice. Learn more.

{
  "name": "emphasis",
  "value": "moderate"
}
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
  }
}