Hebrish
Technical

Speech synthesis models

Text to speech: text in, speech out, with the Hebrew words said the way Israelis say them.

Meorav

A full fine-tune of Qwen3-TTS-12Hz-1.7B-Base on Daniel's voice. Listen to the Before and After samples on the Meorav page.

Meorav New · v2.2

Qwen · Qwen3-TTS 12Hz 1.7B Base

Text-to-speech for code-switched English: Irish-accented English that pronounces the Hebrew words in it correctly. A full fine-tune of Qwen3-TTS; current release v2.2, not benchmarked yet.

Current
Meorav v2.2 (2026-11-09)
Last updated
Formats
Qwen3-TTS (safetensors), GGUF
Parameters
1.9B
Result
No benchmark yet; v2.2 released after Daniel's listening check
DOIs
none yet

Other model groups: Speech recognition models · Accessory models · All models. Use of every Hebrish model is governed by the terms of use.