AhanaVoice

Lessac Amy Kristin HFC Female LJ Speech Kathleen Ryan Joe Bryce John HFC Male Danny
$7.77one mouth $5.005 or more · one file 1 coreno GPU · 140 MB

Measured download files

These are the premade packages on disk, ready to send. Shared packs keep one synthesizer. The “own file” column is that many copies of the measured one-voice package, 58,920,960 bytes.

VoicesShared pack fileEach voice its own fileSharing saves
559,002,880294,604,800235,601,920
1059,013,120589,209,600530,196,480
2559,023,3601,473,024,0001,414,000,640
5059,054,0802,946,048,0002,886,993,920

Shared synthesizer

$5.00 a voice · 5 or more

The file you send is one tar. Five voices: 59,002,880 bytes. Fifty voices: 59,054,080 bytes.

CPU: 1 core. About 12 s to open the compressed synthesizer. About 0.1 s for a short line after that.

GPU: not used.

RAM: about 140 MB once loaded. About 180 MB while speaking. Same for 5, 10, 25, or 50 voices, because only one synthesizer is loaded.

Own synthesizer

$7.77 a voice

Each voice is its own package. One measured file is 58,920,960 bytes. Five of those files are 294,604,800 bytes. Fifty are 2,946,048,000 bytes.

CPU: 1 core for each synthesizer that stays loaded.

GPU: not used.

RAM: about 140 MB for each loaded synthesizer. About 180 MB while that voice is speaking. Five loaded together is about 700 MB.

Packs — click to preview

The card plays the synthesizer inside that package. Download is the compressed file, with a short README. No account and no monthly fee.

Small pack

PACK-small · Lessac · $25 once
File 59,002,880 bytes. 5 voices. One synthesizer. CPU 1 core. GPU none. RAM 140 MB loaded, 180 MB speaking. More voices do not add RAM.

10 voice pack

PACK-10 · Ryan · $50 once
File 59,013,120 bytes. 10 voices. One synthesizer. CPU 1 core. GPU none. RAM 140 MB loaded, 180 MB speaking. More voices do not add RAM.

Large pack

PACK-large · Joe · $125 once
File 59,023,360 bytes. 25 voices. One synthesizer. CPU 1 core. GPU none. RAM 140 MB loaded, 180 MB speaking. More voices do not add RAM.

50 voice pack

PACK-50 · Bryce · $250 once
File 59,054,080 bytes. 50 voices. One synthesizer. CPU 1 core. GPU none. RAM 140 MB loaded, 180 MB speaking. More voices do not add RAM.

Office

PACK-office · HFC Female · $60 once
File 59,013,120 bytes. 12 voices. One synthesizer. CPU 1 core. GPU none. RAM 140 MB loaded, 180 MB speaking. More voices do not add RAM.

Professional

PACK-professional · HFC Male · $60 once
File 59,054,080 bytes. 12 voices. One synthesizer. CPU 1 core. GPU none. RAM 140 MB loaded, 180 MB speaking. More voices do not add RAM.

Fun

PACK-fun · Danny · $60 once
File 59,013,120 bytes. 12 voices. One synthesizer. CPU 1 core. GPU none. RAM 140 MB loaded, 180 MB speaking. More voices do not add RAM.

Humorous

PACK-humorous · LJ Speech · $60 once
File 59,371,520 bytes. 12 voices. One synthesizer. CPU 1 core. GPU none. RAM 140 MB loaded, 180 MB speaking. More voices do not add RAM.

Classic

PACK-classic · Amy · $60 once
File 58,972,160 bytes. 12 voices. One synthesizer. CPU 1 core. GPU none. RAM 140 MB loaded, 180 MB speaking. More voices do not add RAM.

Robot

PACK-robot · John · $60 once
File 59,054,080 bytes. 12 voices. One synthesizer. CPU 1 core. GPU none. RAM 140 MB loaded, 180 MB speaking. More voices do not add RAM.

Accents

PACK-accents · Kathleen · $60 once
File 58,869,760 bytes. 12 voices. One synthesizer. CPU 1 core. GPU none. RAM 140 MB loaded, 180 MB speaking. More voices do not add RAM.

Kenya

PACK-country-kenya · Kristin · $25 once
File 59,432,960 bytes. 5 voices. One synthesizer. CPU 1 core. GPU none. RAM 140 MB loaded, 180 MB speaking. More voices do not add RAM.

Clone

Your clip · one synthesizer
Profile 1,024 bytes. One measured voice package is 58,920,960 bytes. CPU 1 core. GPU none. RAM 140 MB loaded, 180 MB speaking.

Open the clone page

12 mouths — one synthesizer each

Each card is one real mouth. Press Play to hear that synthesizer. Buy is $7.77 once. A style name on a shelf pack uses one of these mouths. It is not a second recording.

House voices — click a face

Same preview as before. Each face speaks through its packaged Piper voice. The product you send is the compressed pack above, not a loose profile.