API Request Stitching

When one has a large text to convert into audio and sends the text in chunks without further context, there can be abrupt changes in prosody from one chunk to another.

It would be much better to give the model context on what was already generated and what will be generated in the future. This is exactly what Request Stitching does; it creates a more seamless flow from one chunk to another by either conditioning on text or past generations. If you've used the Projects feature, you've already experienced the power of this.

Request Stitching Guide: elevenlabs.io/docs/api-referen...