Plugin

Aggiunge Xiaomi MiMo, Doubao, Breeze e la voce del browser a DSH, con adattatori per provider esterni e modelli locali, filtro del testo, lettura vocale in streaming, download audio, effetti sonori, pet desktop e integrazione con QQ Bot e AI Passport.

Balena compagna con ruoli configurabili, voce emotiva tramite TTS locale, memoria persistente su file, messaggistica QQ e chiamate vocali half-duplex. QQ richiede un gateway OneBot v11 compatibile con NapCatQQ. La voce richiede VoiceStudio + audio.cpp + Breeze TTS 2 locali (o un’API TTS compatibile); FFmpeg serve per velocità diverse da 1x.

Client Breeze TTS per DeepSeek Harness: si collega al proprio server/model Breeze TTS, distribuiti separatamente, per leggere le risposte e gestire il voice cloning (requisiti hardware lato server). Modalità tra macchine opzionale. Unisce @dsh-external/dsh-plugin-local-ai-tts (abbccdd/dsh-localtts) e dsh-breeze-voices, include codice di 1624318455/dsh-plugin-tts e non va installato insieme ai due plugin upstream fusi.

Breeze TTS per DeepSeek Harness: legge le risposte per intero o come breve riepilogo, include accesso a Breeze CLI con un clic e importazione automatica della chiave, ricerca e progettazione delle voci, compagnia intelligente e promemoria per pranzo e cena.

Sintesi vocale Breeze Blue per DeepSeek Harness: strumenti agente, riproduzione delle risposte, progettazione della voce e pagina delle impostazioni.

Reads each reply aloud through the BreezeBlue / Breeze TTS 2 API. Synthesis starts as soon as the reply first sentence is complete rather than after the whole reply, and the audio is streamed as raw PCM into Web Audio so it plays continuously while it arrives. Needs a BreezeBlue API key, entered on the settings page or via BREEZE_API_KEY; a key saved on the settings page is stored as plain text in ~/.dsh/breeze-speak.json. By default only the first sentence of each reply (up to 120 characters) is spoken, and that text is sent to api.breeze.blue. The default voice is just an example, so pick one available to your account on the settings page.

BreezeBlue text-to-speech for DSH: three agent tools, a header toggle that reads assistant replies aloud (markdown and code blocks stripped), and local HTTP endpoints for audio playback, synthesis and long-poll delivery. Requires a BreezeBlue API key (BREEZE_API_KEY); synthesis is billed per character.

A model-driven desktop pet, derived from PC2005-cloud/dsh-pet (MIT): an always-on-top companion that follows your agent sessions, races the Web UI to answer approvals and questions, keeps a per-pet affection ledger, speaks through pet_say/pet_do tools or an autonomous inner voice, and can read those lines aloud through BreezeBlue TTS with your own BreezeBlue API key. It uses its own /whale598 route and ~/.dsh/whale598 data directory, so it is a separate pet from dsh-pet rather than a replacement for it.