Clone a voice

Upload a clean reference clip of one speaker and wait for the voice to be ready. 10-30 seconds of clear speech works best: at least 10 seconds, at most 20 MiB.

Cloning requires consent. Passing consent attests that you are the speaker or hold their explicit permission to clone their voice, and the attestation is recorded on the voice. The API rejects clones without it.

import { fileFromPath } from "@flamai/finesse";

const voice = await client.voices.cloneAndWait(
  {
    name: "Ana",
    file: await fileFromPath("reference.wav"), // or a Blob/File, bytes, or { data, filename }
    consent: true,
    language: "en",
    labels: { gender: "female", accent: "british" },
    ref_text: "What the speaker says in the clip, if you have it.",
  },
  { onUpdate: (job) => console.log("clone job:", job.status) },
);

clone_and_wait / cloneAndWait creates the voice, uploads the clip, and polls the clone job until it finishes. The first clone after the cloner has been idle can take a couple of minutes.

Start now, wait later

const clone = await client.voices.clone({
  name: "Ana",
  file: await fileFromPath("reference.wav"),
  consent: true,
});
console.log(clone.voice.status, clone.job_id); // "processing", "6660aa00..."
const ready = await client.voices.waitUntilReady(clone, { timeout: 300_000 });

On the waiting methods, timeout is the overall time to wait for the clone in milliseconds.

When cloning fails

CloneFailedError: the clone job failed.
CloneTimeoutError: the clone didn’t finish in time.

Add a clip to an existing voice

To add a clip to a voice you already created, enroll it:

await client.voices.enroll(voiceId, { file: await fileFromPath("reference.wav"), consent: true });

The HTTP endpoints behind these methods are Clone a voice, Enroll a voice and Get a job.

TypeScript SDK

Reference

Start now, wait later

When cloning fails

Add a clip to an existing voice

​Start now, wait later

​When cloning fails

​Add a clip to an existing voice

Start now, wait later

When cloning fails

Add a clip to an existing voice