Cartesia accent field: multilingual voices only; Sume uses voice id
Cartesia's accent field is for multilingual voices only and works independent of locale. Sume's TTS request has no accent field: pick a voice id and language.
Cartesia's changelog describes a new optional accent field "for multilingual voices only" that sets how the voice sounds while speaking, independent of locale. Sume's TTS 1.0 request documents no accent field; the sound of the result comes from the voice id you send and the language you set.
Where does each choice live in the two APIs?
Cartesia splits the choice across fields; Sume folds it into the voice and the language. Read 2026-10-01.
| Choice | Cartesia | Sume TTS 1.0 |
|---|---|---|
| How the voice sounds | accent, multilingual voices only | The voice id |
| Which voices offer it | Accents field on Get Voice | The voice you pick |
| Level, pace, feeling | Not covered here | generation_config volume, speed, emotion |
How do I choose a voice on Sume?
Send a voice id, or an avatar reference that Sume resolves to its voice. The voice id must be a TTS voice UUID or a Voices library id, "not a voice name from another TTS ecosystem". Anything else is rejected with 400 public_reason=invalid_voice_id before a job is queued or credits are reserved. See the API reference.
Where do I set language and delivery?
Set language for non-English transcripts. generation_config is the optional volume, speed and emotion block. For how language is handled, see Sonic 3.6 languages and the language field.
What if I need a specific accent today?
Audition voices and pick the id that sounds right, then pin it. Do not send a Cartesia voice name; Sume will reject it. For where cloning stands, read voice cloning API.
Sources
Related posts
More in Developers
- Cartesia API version 2026-08-14 and Sume TTS Router model ids
Cartesia's 2026-08-14 API version drops already-deprecated fields; pinned integrations keep running. Pinning on the vendor side, and Sume's explicit model enum.
- 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 normalization: auto, off or a locale code, versus Sume text
Cartesia Sonic 3.6 adds a normalization field set to auto, off or a locale code. Sume TTS has no such field, so write dates and numbers out in the transcript.
- 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.
Written by Sume