Voice Tools
Voice Extend
Continue an audio clip in the same voice. Pass a short reference plus the new text; returns audio that sounds like the original speaker speaking the new content.
POST
Continue an audio clip in the same voice — passes a short reference
clip plus the new text and returns audio that sounds like the
original speaker speaking the new content. Lower-friction than
cloning + synthesizing in two calls when the goal is a single
contiguous-feeling clip.
Authorization
string
required
Bearer token.
Bearer API_key.Request Body
string
required
Source audio URL providing voice + style. 5–30 seconds is the
sweet spot.
string
required
New text to render in the source voice.
string
Output audio format. Options:
wav, mp3. Default: wav.When to use what
Tips
- Reference length matters: longer reference clips capture more of the speaker’s prosody. 15+ seconds substantially improves long-form fidelity over 5-second references.
- Prosody fidelity: voice extend preserves the cadence and emotional register of the reference — useful for podcast-style continuations where consistency matters more than literal word-for-word voice match.