The Language Channel — Text-to-Speech Generator

Use *de:, *en:, *it: etc. per line to set language. One MP3 per line, numbered in order.

Voice Quality Guide:
“Neural2” → Highest quality, newest neural network voice models.
“Wavenet” → Still very high quality (earlier neural models).
“Standard” → Older, lower-quality concatenative voices.
Each line must begin with *xx: (language). Optional per-line speed with sp:N (1 = slowest, 10 = fastest, 5 ≈ 1×). Example: *de sp:7:. If omitted, the global speed slider is used.
0 lines detected
0 characters estimated

Download