Warm Voices
There is no tone field in the catalog, so these were chosen by listening rather than filtered. Warmth is a property of the voice, not a setting, which makes casting the decision that counts.

VOICES FOR THIS USE CASE
Warmth is not a field
The catalog has no tone attribute, so warmth cannot be filtered for and these voices were selected by ear. That is worth stating plainly rather than presenting an inferred list as a filtered one. Audition all six, since the differences between them are not documented anywhere.
Where warmth is usually wanted
Audiobooks, customer support and wellness content are the common contexts, and they pull in different directions. A voice that reads as warm in a support call may be too intimate for narration. Testing against your actual material matters more than a general judgment of tone.
It is a property, not a setting
There is no tone or emotion parameter, so a voice cannot be made warmer after generation. Casting is the decision. The only related control is speed, and slowing slightly below 1.0 tends to read as warmer, though it is a weaker lever than choosing a different voice.
Matching a voice you already use
If your brand already has a warm voice, cloning reproduces it directly rather than approximating it from the catalog. That is the only route to a specific tone, since nothing in the API adjusts toward one. Cloning requires consent from the person whose voice it is.
SPECIFICATION
Sample rate
44.1 kHz native, resampled to 8 kHz for telephony
Latency
~200 ms to first byte (p50, warm region)
Output formats
ulaw, alaw, PCM 16-bit, WAV, MP3
Streaming transports
WebSocket, HTTP chunked transfer
Speed range
0.5× – 2.0×, set per request
Explore Voice Similar to
Warm Voices
FAQs










