Twenty three voices carry the character and animation tag, the group with the widest delivery in the catalog. These six are drawn from it, mixing American, Indian and Japanese accents for dubbing and original work alike.
VOICES FOR THIS USE CASE
What the character tag covers
Twenty three of 244 voices carry the character and animation tag. It is the smallest use-case group and the one with the most range, built for dialogue that performs rather than informs. That suits animation, games and dubbing, where a line has to carry a personality rather than deliver a fact.
Producing lines while the game runs
The WebSocket transport streams audio as it renders, so dialogue can be produced during play rather than pre baked into a build. For a project with branching conversation that stops your asset count multiplying, and it means a script change costs one line rather than a re-render.
Being straight about what this is not
These are human voices with wide delivery, not stylised anime voices. There is no pitch shifting, no formant control and no effects layer, so the very high registers common in Japanese anime are outside what the model produces. If that is what you need, this page will not deliver it and it is better to know now.
Dubbing across languages
A voice covers either the Indic family of eleven languages or the European family of thirteen, and 52 voices reach all 21. For a dub released across several markets, one voice can carry a character through multiple languages instead of recasting per territory.
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
AI Voices for Anime and Animation
FAQs