@pellux/goodvibes-tui 0.19.31 → 0.19.33

package/CHANGELOG.md

@@ -4,6 +4,36 @@ All notable changes to GoodVibes TUI.
 
 ---
 
+## [0.19.33] — 2026-04-26
+
+### Changed
+- `/config-tts` now opens an interactive TTS configuration modal instead of only printing provider and voice lists.
+- `/config-tts providers` and `/config-tts voices [provider]` open selectable provider/voice pickers in the TUI and persist the selected SDK config keys.
+- `/config-tts llm` opens the model picker for a separate `/tts` response-model override; `/tts` still defaults to the current chat provider/model when no override is configured.
+
+### Fixed
+- `/tts` now honors configured `tts.llmProvider`/`tts.llmModel` for that spoken turn without changing the main chat model or global provider settings.
+- Changing the TTS provider clears the provider-specific voice selection so a stale voice id is not reused against a different provider.
+
+## [0.19.32] — 2026-04-25
+
+### Added
+- Live `/tts <prompt>` command for normal chat turns with additional streaming spoken output. Text still renders normally; only turns submitted through `/tts` are spoken.
+- `/tts stop` cancellation for active playback, queued audio chunks, and pending streaming TTS requests.
+- `/config-tts` and `/tts-config` commands for TTS provider, voice, and optional spoken-turn LLM override settings.
+- Local streaming audio playback through `mpv` or `ffplay`, with non-blocking status errors when no player is available.
+- Documentation for live TTS usage, playback requirements, TTS config keys, and the new `POST /api/voice/tts/stream` daemon route.
+
+### Changed
+- Updated `@pellux/goodvibes-sdk` to `0.25.8` and regenerated foundation operator contract artifacts.
+- Exposed provider auth route posture in CLI provider management output.
+- Updated onboarding wizard navigation with an `Apply & Continue To Next Section` action that saves wizard screen state without applying runtime settings before the final review/apply step.
+- Kept prompt borders visually inactive when keyboard focus moves to the process indicator.
+
+### Fixed
+- Updated daemon/media route seam tests for the SDK streaming voice service contract.
+- Added focused regression coverage for text chunking, player discovery, spoken-turn event correlation, and TTS command behavior.
+
 ## [0.19.31] — 2026-04-25
 
 ### Changes

package/README.md

@@ -2,7 +2,7 @@
 
 [![CI](https://github.com/mgd34msu/goodvibes-tui/actions/workflows/ci.yml/badge.svg)](https://github.com/mgd34msu/goodvibes-tui/actions/workflows/ci.yml)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-[![Version](https://img.shields.io/badge/version-0.19.31-blue.svg)](https://github.com/mgd34msu/goodvibes-tui)
+[![Version](https://img.shields.io/badge/version-0.19.33-blue.svg)](https://github.com/mgd34msu/goodvibes-tui)
 
 A terminal-native AI coding, operations, automation, knowledge, and integration console with a typed runtime, omnichannel surfaces, structured memory/knowledge, and a raw ANSI renderer.
 
@@ -988,7 +988,7 @@ These systems are first-class runtime families.
 
 - `web-search`: provider-backed search with verbosity control, evidence shaping, optional source fetching, and normalized results across DuckDuckGo, SearXNG, Brave, Exa, Firecrawl, Tavily, and Perplexity
 - `artifacts`: durable file/object storage for markdown, text, JSON, CSV, spreadsheets, PDFs, images, audio, video, and generated outputs, with metadata, content access, and delivery reuse
-- `voice`: provider-backed TTS/STT/realtime negotiation with OpenAI, ElevenLabs, Deepgram, Google, Microsoft, and Vydra
+- `voice`: provider-backed TTS/STT/realtime negotiation with OpenAI, ElevenLabs, Deepgram, Google, Microsoft, and Vydra; the TUI also supports live `/tts` spoken output through streaming TTS providers and local `mpv`/`ffplay` playback
 - `multimodal`: unified image/audio/video/document analysis with packet building and optional knowledge write-back
 
 These surfaces are exposed through the daemon/API as well as the TUI panels and commands, giving future web and companion clients the same backend runtime.
@@ -1268,6 +1268,8 @@ Those pieces cover conversation-noise routing, panel-health/performance budgets,
 | `/refresh-models` | — | Refresh model catalog, benchmarks, and token limits |
 | `/notify [action]` | `/ntf` | Manage webhook notifications (ntfy.sh): add, remove, list, clear, test |
 | `/voice [action]` | — | Review optional voice posture and export/inspect voice bundles |
+| `/tts <prompt>` | — | Submit a normal prompt and play the assistant response through live TTS |
+| `/config-tts [action]` | `/tts-config` | Open TTS configuration for provider, voice, and optional `/tts` response-model override |
 | `/diff [target]` | `/d` | Show unified diff: session, head, working, staged, or a git ref |
 | `/mcp [tools]` | — | List connected MCP servers and their tools |
 | `/help [command]` | `/h`, `/?` | Show available commands and keyboard shortcuts |