Mistral speech provider

A Mistral speech provider lets Live Hub use your Mistral account for text-to-speech (TTS), through its Voxtral model.

Adding the provider requires the API key from your Mistral account. Mistral'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 a Mistral speech provider

To add a Mistral speech provider:

  1. In the 'Authentication key' field, enter the API key from your Mistral account.

  2. 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.

    The Mistral speech provider fields

  3. Click Create.

Configure advanced parameters at the provider level

The JSON you enter in 'Provider configuration' is merged into every synthesis request Live Hub sends to Mistral, so it applies to every bot connection using this provider.

{
    "ttsConnectionTimeoutMS": 800,
    "ttsRetries": 2
}

The editor validates what you enter against Mistral's schema, so it flags an unknown parameter name or a wrong value type before you save.

Configure advanced parameters at the bot connection level

You can set the same parameters on a single bot connection rather than on the provider, under ttsPassthruConfig in the JSON editor on the connection's Advanced tab. See Manage bot connections.

Language, model, and voice

You select the model and the voice per bot connection, on its Settings tab, not on the provider. See Manage bot connections. The same voice list applies regardless of the model or language you select.