diff --git a/CHANGELOG.md b/CHANGELOG.md
index c38d56b..54a7467 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -9,6 +9,13 @@ Format follows [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
 ### Added
 
+- **Text input in Conversation Playground** — a pill-shaped text field and send
+  button (→) now sit left of the mic button. Typing a message and pressing Enter
+  or → skips STT entirely and sends text directly through LLM → TTS. Makes the
+  playground fully usable without a microphone (HTTP context, no mic permission,
+  remote access). Backend `/api/conversation/turn` now accepts an optional `text`
+  form field; when set, the STT step is skipped and the STT latency row shows `—`.
+
 - **Container name field on all engine cards** — every TTS and STT engine card
   (Docker stack cards *and* static "Other Local" cards) now always shows the
   Docker container name input row. Previously absent/not-installed cards hid it;
diff --git a/routes/conversation.py b/routes/conversation.py
index e0f57db..625baca 100644
--- a/routes/conversation.py
+++ b/routes/conversation.py
@@ -659,7 +659,8 @@ async def conversation_llm_models(url: str = ""):
 
 @router.post("/api/conversation/turn")
 async def conversation_turn(
-    audio:         UploadFile = File(...),
+    audio:         UploadFile | None = File(None),
+    text:          str = Form(""),
     stt_backend:   str = Form("configured"),
     llm_url:       str = Form(""),
     llm_model:     str = Form(""),
@@ -668,21 +669,31 @@ async def conversation_turn(
     system_prompt: str = Form("You are a helpful voice assistant. Keep replies short and conversational."),
     history:       str = Form("[]"),
 ):
-    """Stream a full conversation turn (STT → LLM → TTS) as Server-Sent Events."""
+    """Stream a full conversation turn (STT → LLM → TTS) as Server-Sent Events.
+    Pass either an audio file (runs STT first) or a plain text string (skips STT).
+    """
+    direct_text = text.strip()
+    if not direct_text and (audio is None or not getattr(audio, "filename", None)):
+        raise HTTPException(400, "Provide either an audio file or a text field")
+
     settings = _load_settings()
     eff_llm_url = (llm_url or settings.get("llm_url") or "http://localhost:11434/v1").rstrip("/")
 
-    suffix = Path(audio.filename or "audio.webm").suffix.lower() or ".webm"
-    if suffix not in _UPLOAD_EXTS:
-        suffix = ".webm"
-    tmp = TEMP_DIR / f"{uuid.uuid4().hex}_conv{suffix}"
-    try:
-        with tmp.open("wb") as f:
-            _copy_limited(audio.file, f, _MAX_UPLOAD_BYTES)
-        wav_tmp = _to_wav_16k(tmp)
-    except Exception as e:
-        tmp.unlink(missing_ok=True)
-        raise HTTPException(400, f"Audio upload failed: {e}")
+    # Prepare audio temp files only when an audio upload was provided
+    _tmp: Path | None = None
+    _wav: Path | None = None
+    if not direct_text and audio is not None:
+        suffix = Path(audio.filename or "audio.webm").suffix.lower() or ".webm"
+        if suffix not in _UPLOAD_EXTS:
+            suffix = ".webm"
+        _tmp = TEMP_DIR / f"{uuid.uuid4().hex}_conv{suffix}"
+        try:
+            with _tmp.open("wb") as f:
+                _copy_limited(audio.file, f, _MAX_UPLOAD_BYTES)
+            _wav = _to_wav_16k(_tmp)
+        except Exception as e:
+            _tmp.unlink(missing_ok=True)
+            raise HTTPException(400, f"Audio upload failed: {e}")
 
     try:
         hist = json.loads(history) if history else []
@@ -693,7 +704,6 @@ async def conversation_turn(
 
     stt_be = _clean_stt_backend(stt_backend)
     tts_be = _clean_preview_backend(tts_backend)
-    _tmp, _wav = tmp, wav_tmp
 
     async def generate():
         t0 = time.monotonic()
@@ -703,21 +713,23 @@ async def conversation_turn(
         def sse(obj: dict) -> str:
             return f"data: {json.dumps(obj)}\n\n"
 
-        # 1. STT
-        try:
-            t_stt = time.monotonic()
-            transcript, _ = await asyncio.to_thread(_transcribe_audio, _wav, settings, stt_be)
-            stt_ms = int((time.monotonic() - t_stt) * 1000)
-            yield sse({"type": "transcript", "text": transcript, "stt_ms": stt_ms})
-        except Exception as e:
-            yield sse({"type": "error", "stage": "stt", "message": str(e)})
-            return
-        finally:
-            for p in {_tmp, _wav}:
-                try:
-                    p.unlink(missing_ok=True)
-                except Exception:
-                    pass
+        # 1. STT — skipped when caller sends direct text
+        if direct_text:
+            transcript = direct_text
+            yield sse({"type": "transcript", "text": transcript, "stt_ms": None})
+        else:
+            try:
+                t_stt = time.monotonic()
+                transcript, _ = await asyncio.to_thread(_transcribe_audio, _wav, settings, stt_be)
+                stt_ms = int((time.monotonic() - t_stt) * 1000)
+                yield sse({"type": "transcript", "text": transcript, "stt_ms": stt_ms})
+            except Exception as e:
+                yield sse({"type": "error", "stage": "stt", "message": str(e)})
+                return
+            finally:
+                for p in filter(None, {_tmp, _wav}):
+                    with contextlib.suppress(Exception):
+                        p.unlink(missing_ok=True)
 
         if not transcript.strip():
             yield sse({"type": "error", "stage": "stt", "message": "No speech detected."})
diff --git a/static/js/conversation.js b/static/js/conversation.js
index 4c9b2dd..56c517f 100644
--- a/static/js/conversation.js
+++ b/static/js/conversation.js
@@ -106,6 +106,8 @@ $('s-import-voices-file')?.addEventListener('change', async function () {
   const micIcon       = $('conv-mic-icon');
   const micStatus     = $('conv-mic-status');
   const micTimer      = $('conv-mic-timer');
+  const textInput     = $('conv-text-input');
+  const sendBtn       = $('conv-send-btn');
   const clearBtn      = $('conv-clear-btn');
   const sttSel        = $('conv-stt-select');
   const llmUrlInp     = $('conv-llm-url');
@@ -489,6 +491,110 @@ $('s-import-voices-file')?.addEventListener('change', async function () {
       isProcessing = false;
       micBtn.classList.remove('processing');
       micIcon.className = 'mdi mdi-microphone';
+      if (sendBtn) sendBtn.disabled = false;
+      if (textInput) textInput.disabled = false;
+    }
+  }
+
+  // ── Text-input turn (skips STT, sends text directly) ────────────────────
+  async function processText(text) {
+    text = text.trim();
+    if (!text || isProcessing) return;
+    isProcessing = true;
+    if (sendBtn) sendBtn.disabled = true;
+    if (textInput) { textInput.disabled = true; textInput.value = ''; }
+    micBtn.classList.add('processing');
+    micIcon.className = 'mdi mdi-dots-horizontal';
+    if (micStatus) micStatus.textContent = 'Processing…';
+
+    turnCount++;
+    const turnN = turnCount;
+    const t0 = Date.now();
+
+    const userBubble = addBubble('user', text);
+    const assistantBubble = addTypingBubble();
+    let assistantText = '';
+    let lastStats = null;
+
+    const form = new FormData();
+    form.append('text', text);
+    form.append('stt_backend', sttSel?.value || 'configured');
+    form.append('llm_url', llmUrlInp?.value.trim() || '');
+    form.append('llm_model', llmModelSel?.value || '');
+    form.append('tts_backend', ttsBkSel?.value || 'voice_clone');
+    form.append('tts_voice', ttsVoiceSel?.value || '');
+    form.append('system_prompt', systemPrompt?.value.trim() || 'You are a helpful voice assistant.');
+    form.append('history', JSON.stringify(conversationHistory.slice(-20)));
+
+    try {
+      const resp = await fetch('/api/conversation/turn', { method: 'POST', body: form });
+      if (!resp.ok) throw new Error('Server error ' + resp.status);
+      const reader = resp.body.getReader();
+      const dec = new TextDecoder();
+      let buf = '';
+
+      while (true) {
+        const { done, value } = await reader.read();
+        if (done) break;
+        buf += dec.decode(value, { stream: true });
+        const lines = buf.split('\n');
+        buf = lines.pop();
+        for (const line of lines) {
+          if (!line.startsWith('data:')) continue;
+          let evt;
+          try { evt = JSON.parse(line.slice(5).trim()); } catch(_) { continue; }
+
+          if (evt.type === 'transcript') {
+            if (micStatus) micStatus.textContent = 'Generating reply…';
+          } else if (evt.type === 'token') {
+            if (assistantBubble.querySelector('.conv-typing')) assistantBubble.innerHTML = '';
+            assistantText += evt.delta;
+            assistantBubble.textContent = assistantText;
+            chatWindow.scrollTop = chatWindow.scrollHeight;
+          } else if (evt.type === 'llm_done') {
+            assistantText = evt.text || assistantText;
+            assistantBubble.textContent = assistantText;
+            if (micStatus) micStatus.textContent = 'Synthesising speech…';
+          } else if (evt.type === 'audio') {
+            const mime = evt.mime || 'audio/wav';
+            const binStr = atob(evt.b64);
+            const arr = new Uint8Array(binStr.length);
+            for (let i = 0; i < binStr.length; i++) arr[i] = binStr.charCodeAt(i);
+            const audioBlob = new Blob([arr], { type: mime });
+            const url = URL.createObjectURL(audioBlob);
+            const audio = new Audio(url);
+            audio.onended = () => URL.revokeObjectURL(url);
+            audio.play().catch(() => {});
+            if (micStatus) micStatus.textContent = 'Speaking…';
+          } else if (evt.type === 'stats') {
+            lastStats = evt;
+            updateStats(evt);
+          } else if (evt.type === 'done') {
+            conversationHistory.push({ role: 'user', content: text });
+            conversationHistory.push({ role: 'assistant', content: assistantText });
+            addHistoryItem(turnN, lastStats?.total_ms ?? (Date.now() - t0), true);
+            if (micStatus) micStatus.textContent = 'Ready';
+          } else if (evt.type === 'error') {
+            const wrap = assistantBubble.closest('.conv-bubble-wrap');
+            if (wrap) wrap.remove();
+            addErrorBubble(`[${evt.stage?.toUpperCase() || 'ERR'}] ${evt.message || 'Unknown error'}`);
+            addHistoryItem(turnN, Date.now() - t0, false);
+            if (micStatus) micStatus.textContent = 'Error — ready';
+          }
+        }
+      }
+    } catch(e) {
+      const wrap = assistantBubble.closest('.conv-bubble-wrap');
+      if (wrap) wrap.remove();
+      addErrorBubble(e.message);
+      addHistoryItem(turnN, Date.now() - t0, false);
+      if (micStatus) micStatus.textContent = 'Error — ready';
+    } finally {
+      isProcessing = false;
+      micBtn.classList.remove('processing');
+      micIcon.className = 'mdi mdi-microphone';
+      if (sendBtn) sendBtn.disabled = false;
+      if (textInput) textInput.disabled = false;
     }
   }
 
@@ -502,10 +608,16 @@ $('s-import-voices-file')?.addEventListener('change', async function () {
     }
   });
 
+  // Text input — Enter key or Send button
+  sendBtn?.addEventListener('click', () => processText(textInput?.value || ''));
+  textInput?.addEventListener('keydown', e => {
+    if (e.key === 'Enter' && !e.shiftKey) { e.preventDefault(); processText(textInput.value); }
+  });
+
   clearBtn?.addEventListener('click', () => {
     conversationHistory = [];
     turnCount = 0;
-    chatWindow.innerHTML = '<div class="conv-chat-welcome"><span class="mdi mdi-forum-outline" style="font-size:32px;opacity:.25"></span><p>Press the microphone button below and start talking.</p></div>';
+    chatWindow.innerHTML = '<div class="conv-chat-welcome"><span class="mdi mdi-forum-outline" style="font-size:32px;opacity:.25"></span><p>Type a message or press the microphone button below to start.</p></div>';
     if (turnHistory) turnHistory.innerHTML = '<div class="conv-history-empty">No turns yet.</div>';
     ['cpv-stt','cpv-ttft','cpv-llm','cpv-tts','cpv-total'].forEach(id => { const el = $(id); if(el) el.textContent='—'; });
     ['cpf-stt','cpf-ttft','cpf-llm','cpf-tts','cpf-total'].forEach(id => { const el = $(id); if(el) el.style.width='0%'; });
diff --git a/static/sections/s-conversation.html b/static/sections/s-conversation.html
index e333979..1fcea0f 100644
--- a/static/sections/s-conversation.html
+++ b/static/sections/s-conversation.html
@@ -47,17 +47,26 @@
           <div class="conv-chat-window" id="conv-chat-window">
             <div class="conv-chat-welcome">
               <span class="mdi mdi-forum-outline" style="font-size:32px;opacity:.25"></span>
-              <p>Press the microphone button below and start talking.</p>
+              <p>Type a message or press the microphone button below to start.</p>
             </div>
           </div>
 
-          <!-- Mic bar -->
-          <div class="conv-mic-bar">
+          <!-- Input bar: text field + send + mic -->
+          <div class="conv-input-bar">
             <div class="conv-mic-status" id="conv-mic-status">Ready</div>
-            <button class="conv-mic-btn" id="conv-mic-btn" title="Click to record">
-              <span class="mdi mdi-microphone" id="conv-mic-icon"></span>
-            </button>
-            <div class="conv-mic-timer" id="conv-mic-timer"></div>
+            <div class="conv-text-row">
+              <input id="conv-text-input" class="conv-text-inp"
+                type="text" placeholder="Type a message and press Enter or →"
+                spellcheck="false" autocomplete="off">
+              <button class="conv-send-btn" id="conv-send-btn" title="Send text (Enter)">
+                <span class="mdi mdi-send"></span>
+              </button>
+              <div class="conv-divider" title="or use microphone"></div>
+              <button class="conv-mic-btn" id="conv-mic-btn" title="Click to record via microphone">
+                <span class="mdi mdi-microphone" id="conv-mic-icon"></span>
+              </button>
+              <div class="conv-mic-timer" id="conv-mic-timer"></div>
+            </div>
           </div>
         </div>
 
diff --git a/static/style.css b/static/style.css
index 00dec2b..afb9b1d 100644
--- a/static/style.css
+++ b/static/style.css
@@ -2053,14 +2053,41 @@ code { background: var(--panel); border-radius: 4px; padding: 1px 5px; font-fami
 .conv-typing span:nth-child(3) { animation-delay: .4s; }
 @keyframes convDot { 0%,80%,100% { transform: scale(.7); opacity:.3; } 40% { transform: scale(1); opacity:.9; } }
 
-/* Mic bar */
-.conv-mic-bar { background: var(--surface); border: 1px solid var(--border); border-top: none; border-radius: 0 0 var(--radius) var(--radius); padding: 12px 16px; display: flex; align-items: center; gap: 14px; }
-.conv-mic-btn { width: 52px; height: 52px; border-radius: 50%; border: 2px solid var(--accent); background: var(--accent); color: #fff; font-size: 22px; cursor: pointer; display: flex; align-items: center; justify-content: center; transition: background .15s, transform .1s, box-shadow .15s; flex-shrink: 0; }
+/* ── Conversation input bar (text field + send + mic) ───────────────────── */
+.conv-input-bar {
+  background: var(--surface); border: 1px solid var(--border); border-top: none;
+  border-radius: 0 0 var(--radius) var(--radius); padding: 10px 16px 12px;
+  display: flex; flex-direction: column; gap: 8px;
+}
+.conv-mic-status { font-size: 13px; color: var(--subtext); min-height: 18px; }
+.conv-text-row { display: flex; align-items: center; gap: 8px; }
+.conv-text-inp {
+  flex: 1; min-width: 0; padding: 10px 14px; font-size: 14px; font-family: inherit;
+  border: 1.5px solid var(--border); border-radius: 22px;
+  background: var(--panel); color: var(--text); outline: none;
+  transition: border-color .15s;
+}
+.conv-text-inp:focus { border-color: var(--accent); }
+.conv-text-inp::placeholder { color: var(--subtext); opacity: .7; }
+.conv-send-btn {
+  flex-shrink: 0; width: 40px; height: 40px; border-radius: 50%;
+  border: none; background: var(--accent); color: #fff;
+  font-size: 17px; cursor: pointer; display: flex; align-items: center;
+  justify-content: center; transition: background .15s, transform .1s;
+}
+.conv-send-btn:hover:not(:disabled) { background: #1d4ed8; transform: scale(1.05); }
+.conv-send-btn:disabled { opacity: .4; cursor: default; }
+.conv-divider { width: 1px; height: 32px; background: var(--border); flex-shrink: 0; }
+.conv-mic-btn {
+  flex-shrink: 0; width: 52px; height: 52px; border-radius: 50%;
+  border: 2px solid var(--accent); background: var(--accent); color: #fff;
+  font-size: 22px; cursor: pointer; display: flex; align-items: center;
+  justify-content: center; transition: background .15s, transform .1s, box-shadow .15s;
+}
 .conv-mic-btn:hover { background: #1d4ed8; }
 .conv-mic-btn.recording { background: var(--red); border-color: var(--red); animation: convPulse 1s infinite; }
 .conv-mic-btn.processing { background: var(--yellow); border-color: var(--yellow); cursor: default; }
 @keyframes convPulse { 0%,100% { box-shadow: 0 0 0 0 rgba(220,38,38,.4); } 50% { box-shadow: 0 0 0 8px rgba(220,38,38,0); } }
-.conv-mic-status { flex: 1; font-size: 13px; color: var(--subtext); }
 .conv-mic-timer { font-size: 13px; font-variant-numeric: tabular-nums; color: var(--red); min-width: 36px; text-align: right; }
 
 /* Stats panel */