Files
audio-demo/tts
steve-adminandClaude Sonnet 5 a65532f3b2 Add --instruction and --seed to tts/generate.py
--instruction passes through to MOSS-TTS's build_user_message (confirmed
to work for emotion in earlier testing) so callers can steer per-line
delivery. --seed enables reproducible generation, currently the only
way to get determinism out of this pipeline since MOSS-TTS/AuK don't
use a fixed-seed workflow the way Qwen3 did.

Needed for a downstream per-line episode-generation pipeline (character
cards + emotion-tagged script lines).

Co-Authored-By: Claude Sonnet 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01Y1oQ4h4WE4R9KRvMQLr5Ey
2026-09-15 12:21:10 +00:00
..

tts

Text-to-speech service demos and proofs-of-concept.