Amazon speech provider

An Amazon speech provider lets Live Hub use your AWS account for text-to-speech (TTS) with Amazon Polly, speech-to-text (STT) with Amazon Transcribe, or both.

Amazon's advanced configuration parameters can be set at either of two levels:

If the same parameter is set at both levels, the bot connection value takes precedence.

Add an Amazon speech provider

To add an Amazon speech provider:

  1. From the 'AWS region' drop-down list, select the region your AWS account uses.

  2. In the 'Access key' field, enter the AWS access key ID.

  3. In the 'Secret key' field, enter the AWS secret access key.

  4. Optional: Under Advanced, in the 'Provider configuration' field, enter the advanced configuration parameters that apply to every bot connection using this provider. See Configure advanced parameters at the provider level.

  5. Click Create.

    The Amazon speech provider fields

For speech-to-text, the AWS account needs permission to use Amazon Transcribe.

Configure advanced parameters at the provider level

The JSON you enter in 'Provider configuration' is merged into every request Live Hub sends to AWS, so it applies to every bot connection using this provider. The editor validates what you enter against Amazon's schema, so it flags an unknown parameter or a wrong value type before you save.

Configure advanced parameters at the bot connection level

Amazon's advanced configuration parameters go under sttPassthruConfig and ttsPassthruConfig in the JSON editor on the bot connection's Advanced tab, and Live Hub merges them into the request it sends to AWS. See Manage bot connections.

Text-to-speech

The full set of text-to-speech parameters is SynthesizeSpeechInput in Amazon Polly's SDK documentation.

{
    "ttsPassthruConfig": {
        "LexiconNames": ["example-lexicon"]
    }
}

engine has no effect. Whether Polly uses a neural or a standard voice comes from ttsEnhancedVoice instead, also on the Advanced tab. Amazon's voice list shows which voices support each engine.

Speech-to-text

The full set of speech-to-text parameters is StartStreamTranscriptionCommandInput in Amazon Transcribe's SDK documentation.

{
    "sttPassthruConfig": {
        "EnablePartialResultsStabilization": true
    }
}

Language and voice

You select the language and the voice per bot connection, on its Settings tab, not on the provider. See Manage bot connections.