Skip to content

Open-source platform for 3D AI agents. Turn text or a photo into a rigged, animated GLB avatar, give it an LLM brain, memory and a wallet, and embed it anywhere with one web component. Remote MCP server, x402 payments, Three.js, browser-native.

docs(voice-lab): document the shared-cap on non-BYOK library adds

nirholasb48cac354744
diff --git a/docs/voice-lab.md b/docs/voice-lab.md
index e7c7ad86f..6940b40f1 100644
--- a/docs/voice-lab.md
+++ b/docs/voice-lab.md
@@ -28,7 +28,7 @@ The `providers` array from `GET /api/tts/catalog` is the source of truth: it rep
### The ElevenLabs Voice Library
-The **ElevenLabs Library** tab searches the public catalog ElevenLabs users share (thousands of voices, filterable by accent, age, gender, and use case). A shared voice cannot be synthesized directly: press "Add to my voices" and it is copied into the account behind the request (yours under BYOK, the platform's otherwise), which returns a normal `voice_id` usable everywhere else on the platform.
+The **ElevenLabs Library** tab searches the public catalog ElevenLabs users share (thousands of voices, filterable by accent, age, gender, and use case). A shared voice cannot be synthesized directly: press "Add to my voices" and it is copied into the account behind the request (yours under BYOK, the platform's otherwise), which returns a normal `voice_id` usable everywhere else on the platform. Adding one without BYOK takes one of the shared account's finite voice slots, so it draws on the same 3-per-day budget as cloning (see [States and limits](#states-and-limits)); BYOK adds are uncapped.
## How it works
@@ -146,7 +146,7 @@ The agent-voice handler ([`api/agents/_id/voice.js`](../api/agents/_id/voice.js)
- **A rejected key reads as a key problem.** When ElevenLabs turns down the key on a request, `/api/tts/eleven/voices` and both `/api/tts/eleven/library` methods answer `401 invalid_key` rather than `502`, so the UI can prompt for a new key instead of retrying. A rejected *platform* key still reads as `503 not_configured`, because that one is ours to fix.
- **Voice ids are checked against the lane.** `POST /api/tts/synthesize` rejects a `voiceId` the chosen lane does not publish with `400 validation_error`, naming the id and the catalog URL to pick from, before anything is metered. It is never quietly swapped for the lane default (omit `voiceId` if that is what you want). ElevenLabs, whose catalog grows at runtime, reports an unknown id as a `400` from upstream instead.
- **Paid cloning tier.** Instant Voice Cloning is an ElevenLabs paid-tier (Starter and up) feature. On a free upstream tier the API surfaces the upstream `can_not_use_instant_voice_cloning` body verbatim as a `502`.
-- **Length rules.** Voice Lab recommends 20 to 30 seconds, auto-stops at 60, and rejects under 3. The separate agent-clone endpoint (`POST /api/agents/:id/voice/clone`) enforces a 30-second floor. Platform-key clones on both endpoints are capped at 3 per user per day (an abuse guard on the shared account's limited clone slots) and each is charged per the billing section; BYOK clones on `/api/tts/eleven-clone` skip the cap.
+- **Length rules.** Voice Lab recommends 20 to 30 seconds, auto-stops at 60, and rejects under 3. The separate agent-clone endpoint (`POST /api/agents/:id/voice/clone`) enforces a 30-second floor. Platform-key clones on both endpoints are capped at 3 per user per day (an abuse guard on the shared account's limited clone slots) and each is charged per the billing section; BYOK clones on `/api/tts/eleven-clone` skip the cap. `POST /api/tts/eleven/library` ("Add to my voices" on a shared-library voice) draws on that same 3-per-day budget when it is not BYOK, since it also consumes one of the shared account's finite voice slots; a BYOK add skips it like a BYOK clone.
- **Synthesis limits.** 1,000 characters per `/api/tts/synthesize` request (500 on the older `/api/tts/eleven`); every platform-key request is metered to credits per the billing section (charged before synthesis, refunded on failure). BYOK requests are unmetered by the platform. Clips are cached in R2 and cache hits are not charged.
- **Audio size.** Clone uploads are capped at ~10 MB.
- **"Add to an agent" on `/voice`** links to the dashboard; the actual assignment happens in the agent editor. The cloned `voice_id` lives in browser `localStorage` until you assign it.