Cartesia Instant Voice Clone: up to 60 seconds; Sume takes a voice id

Cartesia says to feed an Instant Voice Clone up to 60 seconds of audio on sonic-3.6. Sume's TTS API does not take reference audio; it takes a voice id.

4 min readSume
All posts

Cartesia's changelog says that on sonic-3.6 an Instant Voice Clone keeps much more of the original speaker's accent, and to feed it up to 60 seconds of audio for the best results. Sume's TTS request does not accept reference audio at all: you send a ready voice id and a transcript.

What does Cartesia say about the 60 seconds?

The changelog describes better accent retention for Instant Voice Clone, "especially rare accents", and says an Instant Voice Clone can now speak several languages natively. It also says existing Instant and Professional clones carry over to Sonic 3.6 with the same voice IDs. Read 2026-10-01.

Cloning input versus Sume TTS input, read 2026-10-01.
ItemCartesia changelogSume TTS 1.0
Reference audioUp to 60 seconds for best resultsNot part of the TTS request
Voice selectorClone voice IDVoice id (UUID or voi_ id) or avatar reference
Text limitNot stated in this entry20,000 characters

What does the Sume TTS API accept as a voice?

A voice id must be a TTS voice UUID or a Voices library id, "not a voice name from another TTS ecosystem". A bad id fails with 400 public_reason=invalid_voice_id before a job is queued or credits are reserved. Details in the API reference.

What does a request cost?

TTS 1.0 is listed at $0.0475 per 1,000 characters. The quote assumes an estimated 1,000 characters, with a minimum of 1 and a maximum of 20,000; spaces and punctuation count. Pass-through Sonic ids in the Router catalog are priced at the TTS 1.0 list times a 1.10 character book.

Can I clone a voice through the API?

Not through the TTS request. Read voice cloning API for what exists today, and ElevenLabs v4 voice clone rules for how another vendor frames consent.

Sources

Related posts

More in Developers

All Developers posts

Written by Sume