Voice cloning

A cloned voice copies the speaker, the room and the microphone of its reference clip: noise, music and a second speaker in the clip come back in every line the voice speaks.

The clip

• Send the exact words of the clip as transcript: every cloning model reads the transcript as reference_text. Without a transcript, the API transcribes the clip on first use and stores the text on the voice.
• Trim silence at both ends. A pause inside the clip is fine.
• Files up to 20 MB in WAV, MP3, M4A, Ogg, WebM or FLAC. The length comes from the file's header; a WebM clip has duration_s null, and only its first 60 s are used.
• In a browser, record at least 15 s and keep the microphone at the same distance throughout.

Consent

A cloned voice is a person's voice. Clone your own voice, or the voice of a speaker who agreed, and write the agreement in consent: who, for what use, and when. Sharing a cloned voice needs the consent note, and only the albastov.com owner account shares voices. Never clone a film or TV character or a public figure. A designed voice (POST /v1/media/voices/design) needs no speaker: the model makes the voice from a description.

Check a saved voice

1. Save the voice with POST /v1/media/voices. status is ready at once, and preview_job names the job making the preview.
2. Wait for preview_url and listen to the preview: the default model reads one neutral sentence in the voice.
3. Speak a paragraph of the text the voice is for. A clone that sounds muffled, echoing or noisy reflects the clip: record again rather than switch models.
4. Try a second model from the voice's models for a different balance of likeness and stability.

The example speaks one paragraph on two models. Set VOICE to a saved voice of the account.

VOICE=vo_hVAiUiqrYyvgKKkBvgzHnh

for MODEL in omnivoice higgs3; do
  curl https://api.albastov.com/v1/audio/speech \
    -H "Authorization: Bearer $ALBASTOV_API_KEY" \
    -H "Content-Type: application/json" \
    -d "{\"model\": \"$MODEL\", \"voice\": \"$VOICE\", \"input\": \"A paragraph in the style the voice is for, read at its usual pace.\"}" \
    --output "check-$MODEL.mp3"
done
ls -l check-*.mp3

Pick a cloning model

Every cloning model, with a sample in the same voice: Audio models. A saved voice's models lists every model that speaks the voice.

Reference

• Voices: clone, design, list, share, copy and delete.
• Voices reference: every route, parameter and error.