@pinecall/skills 0.1.6 → 0.1.8

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@pinecall/skills",
-  "version": "0.1.6",
+  "version": "0.1.8",
   "description": "Agent Skills for the Pinecall SDK — installable into Claude Code, Antigravity, Cursor, Copilot and any agent that supports the open Skills format.",
   "type": "module",
   "license": "MIT",

package/skills/pinecall-reference/references/reference/llm-providers.md

@@ -184,8 +184,25 @@ llm: {
 llm: "xai/grok-4"        // "grok" is accepted as an alias for "xai"
 ```
 
+Or with tuning (same config shape as OpenAI — see [Temperature & max_tokens](#temperature--max_tokens)):
+
+```typescript
+llm: {
+  provider: "xai",
+  model: "grok-4",
+  enabled: true,
+  temperature: 0.7,
+  max_tokens: 512,
+}
+```
+
 OpenAI-compatible. Requires your own xAI key. Models: `grok-4`, `grok-4-fast`, `grok-3`.
 
+> **All BYOK LLM providers below (Groq, Cerebras, DeepSeek, OpenRouter) are
+> OpenAI-compatible** — they take the **identical config object** (`provider`,
+> `model`, `temperature`, `max_tokens`, `enabled`) and support the same tools /
+> tuning as OpenAI. Only the `provider` and `model` change.
+
 ## Groq (BYOK)
 
 ```typescript

package/skills/pinecall-reference/references/reference/managed-vs-byok.md

@@ -21,22 +21,23 @@ Every STT, TTS and LLM model on Pinecall is one of two kinds:
 
 | Service | Managed providers |
 |---|---|
-| **STT** | `deepgram` (flux, nova-3), `gladia`, `transcribe` (AWS) |
+| **STT** | `deepgram` (flux, nova-3), `gladia`, `transcribe` (AWS), `cartesia` (ink-whisper), `elevenlabs` (scribe) |
 | **TTS** | `elevenlabs`, `cartesia` (sonic), `polly` (AWS) |
 | **LLM** | `openai`, `anthropic`, `google` (gemini), `mistral` |
 
+> **One key, both services:** an ElevenLabs (or Cartesia) key serves *both* that
+> vendor's TTS and STT. Pinecall already holds those keys for the managed TTS, so
+> their STT (ElevenLabs **Scribe**, Cartesia **Ink-Whisper**) is **also managed** —
+> no key needed.
+
 ## What requires your own key (BYOK)
 
 | Service | BYOK-only providers |
 |---|---|
-| **STT** | `cartesia` (ink-whisper), `elevenlabs` (scribe), `assemblyai` |
+| **STT** | `assemblyai` |
 | **TTS** | `rime` |
 | **LLM** | `xai` (grok), `groq`, `cerebras`, `deepseek`, `openrouter` |
 
-> Note a provider can be **managed for one service and BYOK for another** — e.g.
-> Cartesia **TTS** (sonic) is managed, but Cartesia **STT** (ink-whisper) is BYOK.
-> ElevenLabs **TTS** is managed, ElevenLabs **STT** (scribe) is BYOK.
-
 ## Check it from the API (authoritative, live)
 
 The rate table is the source of truth. Query it any time:
@@ -55,7 +56,7 @@ curl https://playground.pinecall.io/api/rates/models
     // ...
   ],
   "managedProviders": {
-    "stt": ["deepgram", "gladia", "transcribe"],
+    "stt": ["cartesia", "deepgram", "elevenlabs", "gladia", "transcribe"],
     "tts": ["cartesia", "elevenlabs", "polly"],
     "llm": ["anthropic", "google", "mistral", "openai"]
   }

package/skills/pinecall-reference/references/reference/stt-providers.md

@@ -43,8 +43,8 @@ for the full list and the live `GET /api/rates/models` query.
 | `deepgram` (flux/nova) | ✅ Yes | Default, recommended |
 | `gladia` | ✅ Yes | |
 | `transcribe` (AWS) | ✅ Yes | |
-| `cartesia` (ink-whisper) | ❌ BYOK only | Add a Cartesia key |
-| `elevenlabs` (scribe) | ❌ BYOK only | Add an ElevenLabs key |
+| `cartesia` (ink-whisper) | ✅ Yes | Same key as Cartesia TTS — Pinecall hosts it |
+| `elevenlabs` (scribe) | ✅ Yes | Same key as ElevenLabs TTS — Pinecall hosts it |
 | `assemblyai` (universal) | ❌ BYOK only | Add an AssemblyAI key |
 
 > **BYOK enforcement:** if you configure a BYOK-only STT provider and your org has
@@ -135,10 +135,11 @@ stt: {
 }
 ```
 
-## Cartesia Ink-Whisper (BYOK)
+## Cartesia Ink-Whisper
 
-Pairs naturally with Cartesia (Sonic) TTS for a single-vendor voice stack. Requires
-your own Cartesia key.
+Pairs naturally with Cartesia (Sonic) TTS for a single-vendor voice stack.
+**Managed** — the same Cartesia key serves TTS and STT, and Pinecall hosts it (or
+bring your own Cartesia key to bill it directly).
 
 ```typescript
 stt: "cartesia/ink-whisper"
@@ -146,25 +147,36 @@ stt: "cartesia/ink-whisper"
 stt: { provider: "cartesia", model: "ink-whisper", language: "en" }
 ```
 
-## ElevenLabs Scribe (BYOK)
+## ElevenLabs Scribe
 
-Realtime `scribe_v2_realtime`. Uses the same ElevenLabs key as ElevenLabs TTS.
+Realtime `scribe_v2_realtime`. **Managed** — uses the same ElevenLabs key as
+ElevenLabs TTS, which Pinecall hosts (or bring your own ElevenLabs key).
 
 ```typescript
 stt: "elevenlabs/scribe"
-// or
-stt: { provider: "elevenlabs", model: "scribe_v2_realtime", language: "en" }
+// or with tuning
+stt: {
+  provider: "elevenlabs",
+  model: "scribe_v2_realtime",
+  language: "en",
+  commit_strategy: "vad",   // "vad" (server segments turns) | "manual"
+}
 ```
 
 ## AssemblyAI (BYOK)
 
-Universal-3 streaming (`u3-rt-pro`) — strong accuracy + diarization. Requires your
-own AssemblyAI key.
+Universal-3 streaming (`u3-rt-pro`) — strong accuracy + diarization. **BYOK only** —
+Pinecall hosts no AssemblyAI key, so add your own under Provider Keys.
 
 ```typescript
 stt: "assemblyai/universal"
-// or
-stt: { provider: "assemblyai", model: "u3-rt-pro", language: "en" }
+// or with tuning
+stt: {
+  provider: "assemblyai",
+  model: "u3-rt-pro",
+  language: "en",
+  format_turns: true,   // punctuated/cased final transcripts
+}
 ```
 
 ## Which to choose
@@ -175,8 +187,8 @@ stt: { provider: "assemblyai", model: "u3-rt-pro", language: "en" }
 | `deepgram/nova-3` | Arabic, Hindi, Thai, CJK, and 60+ languages | Slightly higher latency; smart_turn + silero VAD |
 | `gladia/solaria` | Code-switching, multilingual | Higher latency than Deepgram |
 | `transcribe` | AWS-native deployments | AWS pricing model |
-| `cartesia/ink-whisper` | Single-vendor with Cartesia TTS | BYOK only |
-| `elevenlabs/scribe` | Single-vendor with ElevenLabs TTS | BYOK only |
+| `cartesia/ink-whisper` | Single-vendor with Cartesia TTS | Managed (shared key) |
+| `elevenlabs/scribe` | Single-vendor with ElevenLabs TTS | Managed (shared key) |
 | `assemblyai/universal` | Accuracy + diarization | BYOK only |
 
 For most agents, start with `deepgram/flux`. Use `deepgram/nova-3` for languages Flux doesn't cover (Arabic, Hindi, Thai, Chinese, Japanese, Korean, etc.).