Text to Dialogue
By Steven Van ·
Text to Dialogue API requests can now carry context and request IDs between generations, and use the Instant Voice Clone version of a Professional Voice Clone.
Text to Dialogue requests in the ElevenLabs API can now keep continuity across separate generations, and can use a lighter version of a Professional Voice Clone. Both changes were listed in the September 28 changelog.
- Generation continuity: a request can pass preceding or following text (up to 100 characters each) and up to 3 previous or next request IDs, so a new generation can match the ones around it.
- Professional voice mode: setting use_pvc_as_ivc makes a request use the Instant Voice Clone version of a Professional Voice Clone, to reduce latency or improve expressiveness.
The settings object also gains a similarity value from 0 to 1, with a default of 0.75. The JavaScript and Python SDKs at v2.70.0 include the new Text to Dialogue option.
ElevenLabs
AI audio platform for text to speech, voice cloning, and video dubbing across dozens of languages while preserving the original tone and emotion.
View ElevenLabs →