Many African languages are tonal (i.e. there is a specific way to pronounce them properly). In writing, this is indicated by certain marks which can help the reader (human or AI) to properly pronounce such text. We have built this endpoint with model support for African languages.

If Python isn’t your vibe, try using the ReST API directly. Go to the API Reference section. We’re working to add SDKs for more languages.

​
Request

The tone_mark() function can be used to add tone marks to a sentence. Examples are provided below as a guide for you.

​
Response

The response for speech generation is in bytes.

  • The Content-Type is application/json
  • A request_id is returned for issue resolution with our support team.

Below is an example of a response from the API

{
  "request_id": "'86095cea-77d5-45ba-a093-0f800ac2c7df'",
  "text": "Báwo ni olólùfẹ́ mi?"
}

​
Language Support

The speech generation model supports the following languages:

  • Yoruba: yo

Support for Igbo is coming soon. More info on languages can be found on the Languages page

When tone marking a sentence, you should use the language code (e.g. yo, ig) and not the full text.

​
Examples

TranslationVoices