Old Tam rewritten and re-voiced (Gitea #3): a new script in his own voice, an old West Country farmer (Qwen3-TTS cloning one recording, so he's the same man in every line), each line's best take chosen by checking its words with Whisper

assets/audio/CREDITS.md

@@ -55,11 +55,14 @@ nednednerb (https://freesound.org/people/nednednerb/sounds/38250/) and
 (https://freesound.org/people/Dave%20Welsh/sounds/194364/). Thank you.
 
 ## Old Tam's voice
-`voice/` is spoken by **Kokoro** (Kokoro-82M by hexgrad, Apache-2.0,
-https://huggingface.co/hexgrad/Kokoro-82M) with its British "George" voice,
-made a little older (deeper, slower, warmer) by `tools/voice/make_voice.py`.
-The recordings are generated from our own text; rebuild them with
-`tools/voice/make_voice.sh` after changing any line.
+`voice/` is spoken by **Qwen3-TTS** (Qwen3-TTS-12Hz-1.7B by Alibaba's Qwen
+team, Apache-2.0, https://huggingface.co/Qwen; run through mlx-audio, MIT).
+His voice, a reedy old West Country farmer, was designed once from a written
+description by Qwen3-TTS VoiceDesign (`tools/voice/old_tam/`), and every line
+is spoken by cloning that recording. Each line's takes are checked against
+the script by Whisper (OpenAI, MIT; mlx-whisper). The recordings are made from
+our own text; rebuild them with `tools/voice/make_voice.sh` after changing any
+line. (Up to 0.6.1 he was Kokoro-82M by hexgrad, Apache-2.0.)
 
 ## Cinderwild's own (CC0)
 `music/`, `ambience/` and `sfx/synth/` are synthesised from scratch by