Skip to main content

$dialer.setTtsConfig

This method overrides the TTS provider settings of the phone channel used for the current call.

The new settings apply only to the current session and don’t affect the global channel settings. They are used until overridden once again or until the call has finished.

Syntax​

The method accepts an object with the new TTS settings. It is not necessary to pass all provider settings every time: you only need to specify the ones that should be overridden.

// Google provider settings
$dialer.setTtsConfig({
    lang: "tr-TR",
    voice: "tr-TR-Wavenet-E",
});
caution
  • If you specify object properties not supported by the provider, they will be ignored.
  • If you pass something other than an object (like a string), an error will be raised in the script.

The method returns an object with the new provider settings. You can get the current settings during a call using the $dialer.getTtsConfig method.

Provider settings​

Google​

  • lang

    • Synthesized speech language.

  • voice

    • Speech synthesis voice.
    tip
    See the complete list of languages and voices for synthesis in the Google documentation.

  • pitch

    • Voice pitch. Takes an integer or float value from -20 to 20, where -20 means a 20-halftone decrease from the original tone, and 20 means the same increase.

  • speakingRate

    • Synthesized speech rate. Takes an integer or float value from 0.25 to 4, where 1 is the normal voice speed.

  • volumeGain

    • Volume increase in dB relative to the normal voice volume. Takes an integer or float value from -96 to 16. When set to 6, the volume is approximately twice as high as normal.

Yandex​

The list of available settings depends on the TTS version.

You can get the current version during a call via $dialer.getTtsConfig. If the useV3 parameter is set to true, then the third version of the Yandex SpeechKit protocol is used.

caution

Select a version in the connection settings.

Do not change the value of the useV3 parameter via $dialer.setTtsConfig as this can cause TTS errors.

  • lang
    • Speech synthesis language.
  • voice
    • Speech synthesis voice.
  • speed
    • Synthesized speech rate. Takes an integer or float value from 0.1 to 3, where 1 is the normal voice speed.
  • emotion

    • Speaker role, which is a characteristic of the voice. For example, the speaker can sound friendlier or whisper.

      caution

      If you use a role that is not supported for the current voice, a TTS error will occur.

tip

See the complete list of languages, voices, and roles in the Yandex documentation.

Azure​

  • language

    • Synthesized speech language.

  • voiceName

    • Speech synthesis voice.
    tip
    See the complete list of languages and voices for synthesis in the Azure documentation.

  • sampleRate

    • Sample rate.

Aimyvoice​

  • voice
    • Speech synthesis voice.

3iTech​

  • model
    • Speech synthesis language model.
  • sampleRate
    • Sample rate.
  • speed
    • Synthesized speech rate.
  • tone
    • Voice tone.

ElevenLabs​

  • voiceId

    • Voice ID. You can copy it in the ElevenLabs interface.

      note

      The ElevenLabs website is not available for Russian IP addresses.

  • modelId

    • Model for speech synthesis.

  • stability

    • Controls voice stability and synthesis variation. At low values the voice sounds emotional, at high values it sounds monotonous. Accepts values from 0 to 1.

  • similarityBoost

    • Controls how closely the AI should imitate the original voice. Accepts values from 0 to 1.

  • style

    • Enhances the voice’s unique traits for a more expressive delivery. Accepts values from 0 to 1. Values above 0 require more resources and might increase latency.

  • speed

    • Controls the speech rate. Accepts values ​​from 0.7 to 1.2. The higher the value, the faster the speech will be. The default value is 1.0.

How to use​

Some providers, such as Google and Azure, support male as well as female voices for most languages. You can change the bot voice from the script based on some user traits (like their gender or age) or if they want so.

state: SwitchGender
    q!: * switch gender *
    script:
        var provider = $dialer.getAsrProvider(); # Get the current provider name

        if (provider === "google") {
            var voice = $dialer.getTtsConfig().voice; # Get the current voice
            $temp.isMaleVoice = voice.endsWith("B") || voice.endsWith("D"); # Male voices end with B and D

            var newVoiceLetter = (isMaleVoice ? ["A", "C"] : ["B", "D"])[$reactions.random(2)];
            $dialer.setTtsConfig({ voice: "en-US-Wavenet-" + newVoiceLetter });
        } else {
            # For other providers, the properties and values to be overridden may be different
        }
    a: I am now speaking a {{$temp.isMaleVoice ? "female" : "male"}} voice.