Instant voice cloning

Instant — zero-shot — voice cloning produces a synthetic voice from a short reference clip at request time, with no training job and no per-voice model. Ours takes about ten seconds of audio.

10 s

of reference — the whole enrollment

Instant vs trained cloning

Trained cloning fits a model to hours of a speaker’s audio over hours or days, per voice, often per language. Zero-shot cloning conditions a single model on a reference clip inside the request itself: send ten seconds of the speaker, get that identity back in the synthesis. New voice, no pipeline.

Table 1 — The two cloning disciplines, side by side

	Trained cloning	Zero-shot cloning
Enrollment	hours of audio, per voice	~10 seconds, in the request
Wait	a training job — hours to days	none — first request pays a cache fill
New language	often a new training run	same reference, 23 languages
Cost per voice	a per-voice fee or job	nothing marginal

The cross-language test

The hard version of cloning is speaking a language the reference never spoke — the identity has to survive with none of the original phonemes to lean on. That hard case held up in blind listening panels, and it is the property live translation depends on. One reference carries one identity across 23 languages.

Related sheets.

use case

TTS for live voice translation

Spex-TTS grew out of a production live-translation product. One cloned identity across 23 languages, 107 ms first audio, measured on the production API.

glossary

~1.5 MB

Voice cloning reference audio

The reference is the clip a zero-shot clone is built from: about ten seconds of one clean, consenting speaker, a ~1.5 MB cap, fingerprinted and cached.

capability

never

Provenance and privacy, applied at generation

The policy surface of the engine: an inaudible watermark on every sample, reference audio that never trains, and per-key audit trails at GET /v1/usage.

Every term on this page is measurable on a live call — watch the readout while your own script synthesizes.

See the measured figures live