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.
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.
| Item | Cartesia changelog | Sume TTS 1.0 |
|---|---|---|
| Reference audio | Up to 60 seconds for best results | Not part of the TTS request |
| Voice selector | Clone voice ID | Voice id (UUID or voi_ id) or avatar reference |
| Text limit | Not stated in this entry | 20,000 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
- Green screen removal by API: chromakey in a video filter graph
Sume's video filter allowlists chromakey and colorkey, but an MP4 holds no alpha, so a key must be composited inside the graph. Not AI background removal.
- Agent SDK permissionMode omitted: auto mode, Sume gates stay
From Agent SDK 0.3.286 an omitted permissionMode can start in auto mode. Sume's idempotency_key and scope checks run server-side whatever mode you pick.
- Agent SDK rewind_conversation and a Sume job: find, then cancel
After rewind_conversation or a priority-now message, the MCP call is handled client-side. A submitted Sume job has its own id: find it with jobs_list.
- Claude Code: disable an MCP server mid-session, Sume jobs persist
Switching off an MCP server in Claude Code SDK sessions removes its tools for new calls. Sume jobs already submitted keep running until you read or cancel them.
Written by Sume