🎙️ dsh-talk
- 1024 store channel:
npm i -g dsh1024 once, then dsh1024 plugin --profile web add dsh-talk (counts toward the deepseek1024.com install ranking).
Voice-first session loop for DeepSeek Harness: talk to it, hear it answer.
Press the mic, speak, and the reply is spoken back — with speak-to-interrupt.
English · 简体中文 · Español · Português · हिन्दी
Compatibility
| Surface | Status |
|---|
| Harness | DeepSeek Harness dsh-v0.1.6-alpha.2 (adapted 2026-09-18: third peer clause + engines.dsh + manifestVersion: 1, and the monthly Compat workflow anchored to that line); full gate chain green on 2026-09-18 (dual typecheck rulers, 86 tests, build, self-contained, artifacts, pack). npm dev/test line 0.1.5-rc.2, peers `>=0.1.2-rc.1 <0.2.0 |
| Node | ^22.19.0 || >=24.0.0 |
| Browser | Web Speech + MediaRecorder (Chrome/Edge best); host transcription/TTS engines for the rest |
What you get
dsh-talk closes the voice loop in both directions:
speak tool — the agent speaks its replies aloud. TTS engines: the browser voice, edge-tts (network neural voices), or piper (local). Audio plays in the browser; on hosts that can carry it, the session log records the sanitized utterance (see Security boundaries).- Composer mic button — press it, speak, and the transcription lands in the input box (or submits directly). STT engines: the browser's Web Speech (interim results included), a FunASR HTTP server, or local
whisper.cpp.
- Speak-to-interrupt — starting to talk stops whatever is playing (client → host over the
talk Remote namespace).
- Event announcements — turn completion, pending approvals (waterfall-safe: never blocks the gate), and errors, with a mute switch and configurable phrases.
- Settings tab — engine/language selects and announcement switches, saved as append-only profile-patch operations with backups.
browser host
🎙 press ──▶ interrupt ─────────────────▶ talk/interrupt
record (MediaRecorder / Web Speech)
transcribe (browser) or talk/transcribe ─▶ FunASR / whisper.cpp
setDraft(text) or submit() ◀── talk:speech projection ── speak tool / announcements
▶ play audio (talk/audio or speechSynthesis)
Quick start
# 1. install the bundle into your profile
dsh plugin --profile web add "github:PerryLink/dsh-talk#main"
# or from npm (published releases)
dsh plugin --profile web add dsh-talk
# 2. restart and verify the row
dsh --profile web --dump-config | grep -A2 'id: talk'
Then press the microphone next to the composer and talk; ask the agent to speak its reply:
> Say "hello" with the speak tool.
Install & uninstall
- git channel (latest
main): dsh plugin --profile web add "github:PerryLink/dsh-talk#main" — the prepare script builds with production dependencies only.
- npm channel (published releases):
dsh plugin --profile web add dsh-talk.
- tarball channel:
pnpm pack in this repo, then dsh plugin --profile web add ./dsh-talk-<version>.tgz.
- uninstall:
dsh plugin --profile web remove dsh-talk (or remove the row from the profile patch).
If pnpm reports ERR_PNPM_IGNORED_BUILDS for this package (esbuild's harmless platform-binary validation), add allowBuilds: { esbuild: true } to your pnpm-workspace.yaml — the dsh CLI prints the exact snippet.
Configuration
All tunables are Schemastery Config fields (changeable from cordis.yml). cordis.patch.yml documents each key inline.
| Key | Default | Meaning |
|---|
record.enabled | true | Show the composer mic button |
record.hotkey | (none) | Optional toggle hotkey, e.g. "alt+r" |
record.maxSeconds | 60 | Recording cap in seconds (1..600) |
record.autoSubmit | false | Submit the transcription as a user message (false = fill the draft) |
record.vad.enabled / silenceMs / energyThreshold | true / 1500 / 0.01 | Voice-activity detection: silence auto-ends the recording (degrades when AudioContext is absent) |
stt.engine | auto | auto / web / funasr / whisper; auto prefers a configured local engine, then Web Speech |
stt.language | auto | BCP-47 language or auto |
stt.interim | true | Show interim transcriptions (Web Speech) |
stt.silenceFinaliseMs | 4000 | Stop continuous Web Speech recognition after this many milliseconds without speech (500..15000) |
stt.funasr.url | (none) | FunASR inference endpoint; required when the engine is funasr |
stt.whisper.modelPath | (none) | whisper.cpp model; required when the engine is whisper |
tts.engine | auto | auto / browser / edge-tts / piper; auto prefers piper, then edge-tts, then the browser voice |
tts.rate | 0 | Rate offset in percent (-50..50) for edge-tts/piper |
|
stt.silenceFinaliseMs and record.vad.silenceMs are separate mechanisms: the first finalises the Web Speech transcript when continuous recognition hears no speech, the second is the MediaRecorder energy-based detector that ends the recording (and submits it when record.autoSubmit is on). They run in different pipelines and share no state.
Tools & surfaces
| Surface | Kind | Notes |
|---|
speak | tool | Speaks text aloud (browser/edge-tts/piper); per-call engine/voice overrides; canonical JSON outcome |
| mic button | conversation.input.left slot | Record → transcribe → fill draft (or submit); speak-to-interrupt on press |
| settings tab | settings.plugins.tab (id talk) | Engine/language/announcement switches; append-only save |
talk:* | Typert Remote | status, audio, transcribe, applySettings, interrupt (host namespace) |
Permissions & data
- Permissions: the plugin stores nothing but an in-memory, byte-capped audio cache; microphone permission is browser-mediated. The settings tab only appends patch fragments to the profile with a timestamped backup — never rewrites the file.
- Data: audio never enters the model context or the session log. Where the host's session vocabulary accepts it, the
dsh-talk/speech event carries the utterance id, engine, reason, size, sanitized text, and browser voice/rate/pitch when applicable; on envelope-less hosts the event is not written at all. All display/log surfaces redact credentials, JWTs, bearer headers, and temp paths.
- Network: only the engines you configure are contacted.
edge-tts performs network synthesis, FunASR uses its configured endpoint, and Chrome's webkitSpeechRecognition sends microphone audio to Google's servers for transcription; browser speechSynthesis playback remains local.
Security boundaries
- Model-visible ⟺ logged — the model sees only the speak tool's canonical value and render text. The
dsh-talk/speech event is appended only when the host can carry it (see Host compatibility); the tool/call + tool/result events always remain the reconstructable trail.
- Approval announcements never block — the
approval/request listener always calls next().
- Sanitized output — credentials and temp audio paths never reach logs or displays.
- Host compatibility — the
dsh-talk/speech event is appended through a yes/no gate. Hosts whose known-type vocabulary covers the event append it, and the call reports that it did; every other host — every released line through 0.1.1-rc.2, the 0.1.2-alpha line, 0.1.2-rc.1, and also 0.1.6-alpha.2, whose Session.append can stamp only the surface intent and not the ignorable envelope (that field is retained for stored-log read compatibility only) — gets no append, so speech can never pollute the session log there. The skip is not silent any more: the host keeps per-session appended/skipped counters and talk/latest(sessionId) reads them back, the client's session-scoped playback list stays empty, and the speak tool results remain the reconstructable audit trail.
- Fail loud — invalid engines, out-of-range values, and engines configured without their required model/endpoint fail the mount.
Known limitations
- Browser support: Web Speech and MediaRecorder are feature-detected; without them the mic button disables itself and host engines (FunASR/whisper.cpp) can still transcribe when configured.
- Local engines are your install:
edge-tts, piper, and whisper.cpp executables and models must be installed separately.
- Recording format: the browser records with its native MediaRecorder codec; whisper.cpp may require a WAV-configured recorder or a server-side conversion for other formats.
- Settings apply on reload: the settings tab appends to the profile patch; a profile reload (or web-app restart) activates the changes.
- Live playback history is empty on hosts without the vocabulary: on
0.1.1-rc.2, the 0.1.2-alpha line, 0.1.2-rc.1, and 0.1.6-alpha.2 the host vocabulary does not know dsh-talk/speech, so the gate writes nothing and the client's session-scoped playback list stays empty; talk/latest(sessionId) still answers with the newest utterance and the skipped counter. Speech itself, the mic, the settings tab, and the tool are unaffected.
- Legacy logs written by dsh-talk ≤ 0.2.1 may need repair before cold load: versions through
0.2.1 appended unmarked dsh-talk/speech events. On hosts 0.1.0-rc.7 and newer, a session whose log already contains them fails its next cold load with SessionFormatUnsupportedError. Repair: stop the host, back up the session's .jsonl log, add "ignorable":true as a top-level member of every JSON line whose "type" is "dsh-talk/speech" (for example, insert "ignorable":true, right after the opening {), then reopen the session. Nothing else changes and nothing is lost; new appends from this version never add unmarked events.
Development
pnpm install # node ^22.19 || >=24
pnpm run typecheck # tsc: src + tests against the local harness checkout
pnpm run typecheck:ci # tsc against the published 0.1.5-rc.2 types (no paths)
pnpm test # vitest: 86 tests, 15 suites
pnpm run build # tsc declarations + tsdown bundles (lib/)
pnpm run verify:self-contained # dependency specs resolve from the registry
pnpm run verify:artifacts # built ESM faces + client ModuleLoader handshake
pnpm pack # the published tarball
Topics
dsh, dsh-plugin, deepseek-harness, deepseek, cordis, voice, speech, tts, stt, speech-to-text, text-to-speech, microphone
Contributors
- @PerryLink — creator and maintainer: speak pipeline, speech engines, mic recorder, event announcements, projection unit, and the five-language docs.
PerryLink DSH Plugin Family
This project is one of the 40 DeepSeek Harness plugins maintained by PerryLink. If this one helps you, the others likely will too:
| Plugin | One-liner |
|---|
| dsh-auto-review | Second-model auto-review on the approval chain, fail-closed by default |
| dsh-background-agents | Durable background child agents with a Web UI sidebar, messaging and interrupt |
| dsh-budget | Cost governance for DeepSeek Harness: budgets, carbon, and latency in one panel. |
| dsh-checkpoint-rewind | Claude Code /rewind-equivalent: snapshots, session forks, one-shot restore |
| dsh-claude-move | Migrate Claude Code sessions, memory, skills and CLAUDE.md into DSH |
| dsh-click | Cross-platform native desktop control for DeepSeek Harness — Windows first. |
| dsh-composer-history | Terminal-style input history for the web composer: arrows, Ctrl+R search |
| dsh-data-quality | Dataset quality checks and citation cross-checks (the optional numeric bridge consumed here) |
| dsh-defend | Prompt-injection, jailbreak, and secret-leak defense for DeepSeek Harness. |
| dsh-doublecheck | Engineering-discipline guard: requirements grill, test gates, adversary review |
| dsh-draw | Unified static-image generation routing for DeepSeek Harness. |
Install from the DSH Desktop Market
All PerryLink plugins are browsable in the built-in DSH Desktop Market: Market → Sources → add source → paste https://perrylink-dsh-catalog.perrylink.workers.dev/catalog-source.json → select it. Installation still goes through the Market's npm-identity verification and your confirmation.
License
Apache License 2.0 © 2026 dsh-talk contributors
