Pocket TTS

Fast 100M-parameter speech synthesis with 26 voices across six languages and optional authorized voice cloning from a sample.

Deploy & run Source

RTX 3090 scale to zero MP3, Opus, or WAVTTSmultilingualvoice cloning

Canonical example

Input and output, side by side

Streaming audio output

01 · input

Audio output

text

Kia ora. Your scale-to-zero voice model is ready.

voice

alba

format

mp3

02 · MP3, Opus, or WAV

Audio output

Run the same recipe everywhere

curl -sX POST https://app.nz/api/cogs/run \
  -H "Authorization: Bearer $APP_NZ_KEY" \
  -H "Content-Type: application/json" \
  -d '{"template":"pocket-tts","input":{"text":"Kia ora. Your scale-to-zero voice model is ready.","voice":"alba","format":"mp3"}}'