Spitch

Spitch provides text-to-speech voices for English and African languages. Spitch tuning is passed in synthesizer.options.

{
  "verb": "say",
  "text": "Hi there, your order ships today.",
  "synthesizer": {
    "vendor": "spitch",
    "language": "en-US",
    "voice": "lina",
    "options": {
      "speed": 1.1
    }
  }
}

You can also set these in the portal under Extra Options on the speech credential, in which case they apply to every request that uses that credential. Settings supplied on the verb take precedence.

Credential

Create an API key in your Spitch account. jambonz sends the key as Authorization: Bearer <api key>. Add it as a Spitch speech credential in the portal or API, using the vendor id spitch. Spitch is used for text-to-speech only.

The credential can also set an API host; see Endpoint override.

Voices and languages

Spitch has no model setting. The portal lists these voices, grouped by the language they were designed for:

Every voice can speak every language. jambonz sends the language code from synthesizer.language without its region: en, yo, ha, ig or am. Any other language, including Nigerian Pidgin, is not sent, and the voice speaks the text as written.

jambonz requests Spitch audio as 16-bit PCM at 24 kHz and resamples it to the call’s rate.

Options

Every option is optional. An option you don’t set is not sent, so Spitch’s own default applies.

Endpoint override

To use a different Spitch endpoint, set the API base URL on the credential, or api_uri in its Extra Options or in synthesizer.options. It is a host name such as api.spitch.app; a scheme and trailing / are accepted and ignored. Leave it out to use api.spitch.app.

Streaming

Spitch has no token-streaming websocket, so it does not support TTS streaming: use it for one-shot say, not for say with stream: true or the agent verb.