text and instructions on the preview. Speaker consent is required; see voice consent.
Sample requirements
- Upload exactly one sample file.
- Use a single speaker with no background music or noise.
- Use MP3 or WAV.
- Duration: 5 to 90 seconds.
- Maximum file size: 5 MB.
Step 1: Create a preview
generated_voice_id, not a saved voice_id. text defaults to the Breeze clone script when omitted or empty. instructions defaults to none. SDKs also accept files with exactly one item.
Step 2: Stream the preview
Step 3: Save the preview as a voice
language_code is omitted, Breeze reuses the generation language; legacy previews without language metadata fall back to en.
POST /v1/text-to-speech/{voice_id} calls use the original uploaded sample and transcript, not the preview audio.
Editing or deleting a saved voice
- Update labels and the description with
PATCH /v1/voices/{voice_id}. - Tune defaults with
PATCH /v1/voices/{voice_id}/settings. - Remove the voice with
DELETE /v1/voices/{voice_id}.
Continue building
Create clone preview
Upload one audio sample and inspect the
name, text, and instructions request fields.Stream voice preview
Listen to a
generated_voice_id preview before deciding to save it.Save voice preview
Persist the preview as a reusable voice; saving consumes a voice slot.
CLI voice clone
Clone from an audio sample in the terminal with
breeze voice clone.Voices
Learn how cloned voices, designed voices, public voices, and voice settings fit together.
Text to speech
Use the saved cloned voice for dialogue lines, previews, or production audio.

