Plugins

Adiciona Xiaomi MiMo, Doubao, Breeze e voz do navegador ao DSH, com adaptadores para fornecedores externos e modelos locais, filtro de texto, leitura em voz alta contínua, transferências de áudio, efeitos sonoros, mascote de ambiente de trabalho e integração com QQ Bot e AI Passport.

Companheira baleia com papéis configuráveis, fala emocional via TTS local, memória persistente em arquivo, mensagens QQ e chamadas de voz half-duplex. QQ requer gateway OneBot v11 compatível com NapCatQQ. A voz requer VoiceStudio + audio.cpp + Breeze TTS 2 locais (ou API TTS compatível); FFmpeg é necessário para velocidade diferente de 1x.

Cliente Breeze TTS para DeepSeek Harness: conecta-se ao seu servidor/model Breeze TTS, implantado separadamente, para ler respostas e gerenciar clonagem de voz (requisitos de hardware ficam no servidor). Modo entre máquinas opcional. Reúne @dsh-external/dsh-plugin-local-ai-tts (abbccdd/dsh-localtts) e dsh-breeze-voices, inclui código de 1624318455/dsh-plugin-tts e não deve ser instalado junto dos dois plugins upstream incorporados.

Breeze TTS para DeepSeek Harness: lê as respostas completas ou um resumo curto, oferece login de um clique no Breeze CLI com importação automática de chave, busca e criação de vozes, companhia inteligente e lembretes de almoço e jantar.

Texto para fala Breeze Blue para DeepSeek Harness: ferramentas de agente, reprodução de respostas, design de voz e página de configurações.

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.