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.
JavaScript 3d-generationai-agentsanimationavatardigital-humangenerative-aiglbgltfimage-to-3dllmmcpmcp-servermodel-context-protocolsolanatext-to-3dthreejsweb-componentswebglwebxrx402
fix(tts): report a key ElevenLabs rejected as the caller's 401, not a 502
nirholasf55bcd20a0ca
diff --git a/api/_lib/elevenlabs.js b/api/_lib/elevenlabs.jsindex e3a38dc5e..9a5a7c0d1 100644--- a/api/_lib/elevenlabs.js+++ b/api/_lib/elevenlabs.js@@ -127,7 +127,12 @@ export async function listVoices({ force = false, apiKey: keyOverride = null } =}if (!resp.ok) {console.error('[elevenlabs] listVoices error', resp.status);- throw upstreamError(`ElevenLabs returned ${resp.status}`, 502);+ // `status` stays 502 so existing callers are unchanged; `upstreamStatus`+ // lets a handler that knows whose key it sent tell "their key is wrong"+ // (401) apart from "ElevenLabs is broken" and answer accordingly.+ throw upstreamError(`ElevenLabs returned ${resp.status}`, 502, {+ upstreamStatus: resp.status,+ });}const data = await resp.json();diff --git a/api/tts/eleven/library.js b/api/tts/eleven/library.jsindex af349de1b..5ec543385 100644--- a/api/tts/eleven/library.js+++ b/api/tts/eleven/library.js@@ -95,6 +95,10 @@ async function handleGet(req, res, apiKey) {if (!resp.ok) {const detail = await resp.text().catch(() => '');console.error('[tts/eleven/library] upstream error', resp.status, detail.slice(0, 300));+ // Match handlePost: a rejected key is the caller's problem to fix, not a+ // gateway fault they should retry.+ if (resp.status === 401)+ return error(res, 401, 'invalid_key', 'ElevenLabs rejected the key on this request');return error(res, 502, 'upstream_error', `ElevenLabs returned ${resp.status}`);}@@ -153,7 +157,9 @@ async function handlePost(req, res, apiKey, userId) {} catch {// Non-JSON body: keep the status-only message.}- return error(res, resp.status === 401 ? 401 : 422, 'upstream_error', message);+ return resp.status === 401+ ? error(res, 401, 'invalid_key', 'ElevenLabs rejected the key on this request')+ : error(res, 422, 'upstream_error', message);}const data = await resp.json().catch(() => ({}));diff --git a/api/tts/eleven/voices.js b/api/tts/eleven/voices.jsindex 54f2dcb82..843587ad3 100644--- a/api/tts/eleven/voices.js+++ b/api/tts/eleven/voices.js@@ -44,6 +44,20 @@ export default wrap(async (req, res) => {result = await listVoices(source === 'platform' ? {} : { apiKey });} catch (e) {console.error('[tts/eleven/voices] listVoices failed', e);+ // ElevenLabs rejecting the key is not a gateway fault. When the key came+ // from the caller (an x-eleven-key header or one they saved), say so at+ // 401 so the client can prompt for a new key instead of retrying a 502+ // that will never clear.+ if (e.upstreamStatus === 401) {+ return error(+ res,+ source === 'platform' ? 503 : 401,+ source === 'platform' ? 'not_configured' : 'invalid_key',+ source === 'platform'+ ? 'ElevenLabs rejected this server key'+ : 'ElevenLabs rejected your key. Check it at /dashboard/account.',+ );+ }return error(res,e.status || 502,diff --git a/docs/api-reference.md b/docs/api-reference.mdindex 321ed28b4..e2816311d 100644--- a/docs/api-reference.md+++ b/docs/api-reference.md@@ -874,7 +874,9 @@ Search the public catalog ElevenLabs users share (`q`, `gender`, `accent`,`POST { publicUserId, voiceId, name }` to copy one into the account behind therequest (yours with `x-eleven-key`, the platform's otherwise). The POST returnsa normal `voice_id` usable with `/api/tts/synthesize`. Both require auth and an-ElevenLabs key.+ElevenLabs key. A key ElevenLabs rejects returns `401 invalid_key` (here and on+`/api/tts/eleven/voices`), so a client knows to ask for a new key rather than+retry a `502` that will never clear.### Text-to-speech (ElevenLabs, streaming)diff --git a/docs/voice-lab.md b/docs/voice-lab.mdindex a22b3aa61..b50bec1bd 100644--- a/docs/voice-lab.md+++ b/docs/voice-lab.md@@ -143,6 +143,7 @@ The agent-voice handler ([`api/agents/_id/voice.js`](../api/agents/_id/voice.js)- **Recorder states.** `idle` -> `recording` (live waveform, timer, level meter) -> `review` (playback, name, Clone / Re-record) -> `cloning` (spinner) -> `done` (green check, `voice_id` shown, actions: Try in playground / Add to an agent / Record another).- **Auth.** The free lanes (Edge, Gemini, NVIDIA) serve anonymous callers on `/api/tts/synthesize` and `/api/tts/catalog`, rate-limited per IP. The metered lanes (OpenAI, ElevenLabs), cloning, and the Voice Library return `401 unauthorized` without a session or bearer token.- **Server config.** ElevenLabs must be configured (`ELEVENLABS_API_KEY`) or the endpoints return `503 not_configured`; a request carrying its own `x-eleven-key` header still works (see the billing section above). `/api/tts/eleven-clone` checks who is asking first, so a signed-out caller gets `401` and never a reading of what this deployment has configured.+- **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.diff --git a/prompts/swarm-100/api-tts-01.md b/prompts/swarm-100/api-tts-01.mddeleted file mode 100644index 061148e65..000000000--- a/prompts/swarm-100/api-tts-01.md+++ /dev/null@@ -1,109 +0,0 @@-# API audit: api/tts batch 01 (9 files)--How to run: paste this file's repo path into a fresh Claude Code chat in this-repository and say "run this work order". This file is fully self-contained:-it depends on no other prompt file anywhere. If neighboring files in-prompts/swarm-100/ are gone, that work is done; if present, ignore them.-Every claim below rots; step 0 re-measures, and what you measure wins.--## Operating clause (binding)--- Read CLAUDE.md first. Its rules override everything, including this file.-- Finish 100% in this session. Never end the turn with a question, an option- list, or an unexecuted plan. A judgment call goes in one line of the final- report; it never becomes a question that halts work.-- The only permitted stops are the CLAUDE.md stop-and-ask gates: spending real- funds or any irreversible on-chain write, git push or a production deploy,- committing content that references a crypto project other than $THREE, and- destroying unrecoverable data.-- No mocks, no fake data, no placeholder stubs, no unfinished-work markers, no- commented-out code. Real APIs and real integrations only.-- The em-dash and en-dash characters are banned in everything you write.-- Concurrent agents share this worktree: stage explicit paths only (never a- bare add-everything), and commit finished work promptly.-- Before committing, run: npm run check:rules -- --paths <files you touched>.- It must exit 0.--## Step 0: re-derive the current state--1. Confirm each file below still exists; deleted ones are done, skip them.-2. For each, decide routability: grep its path in vercel.json and read how- server/index.mjs maps filesystem handlers. Routed files get an endpoint- audit; internal modules get a code and test audit.-3. Start a local server for endpoint checks: node server/index.mjs with .env- loaded, on a free PORT if 3000 is busy.--## Task: audit these api files, then fix everything found--Files in this batch:--- api/tts/catalog.js-- api/tts/edge.js-- api/tts/eleven-clone.js-- api/tts/eleven.js-- api/tts/eleven/library.js-- api/tts/eleven/voices.js-- api/tts/speak.js-- api/tts/synthesize.js-- api/tts/voices.js--For every routed handler:--1. Exercise it with curl against the local server: the success path returns- real data with the correct status; malformed input returns a 4xx JSON- error, never a stack trace or an HTML error page; auth is enforced where- the code intends it; CORS matches neighboring handlers.-2. Hard-rule scan: no mock fallbacks, no fake-data arrays, no stubbed- responses, no unfinished markers. Errors are handled at the boundary and- internal code trusts itself.-3. Do not spend funds or sign anything on-chain while probing. Payment and- trading handlers get their validation and error paths exercised, never a- live settlement.--For every internal (non-routed) module:--4. Something must import it; if nothing does, delete it as dead code (verify- with a repo-wide grep first).-5. Its main path and one failure path must be covered in tests/; add the- missing test if not.--## Definition of done--- [ ] Every listed file has recorded evidence: a curl transcript for routed- handlers, a passing test or a deletion for internal modules.-- [ ] Zero hard-rule violations remain in these files.-- [ ] vitest run passes; npm run check:rules -- --paths <touched files>- exits 0.--## Never blocked--| Blocker | Resolution (act, do not ask) |-|---|---|-| Missing env var or credential | Check .env and .env.local, then the Cloud Run service env, then Secret Manager (the CLAUDE.md self-unblock playbook has the exact commands). If it truly exists nowhere, wire the code fully behind the env var, prove the wiring with a dry run, and name the single missing var in the report. |-| gcloud not on PATH | Run: export PATH="$HOME/google-cloud-sdk/bin:$PATH" |-| Dev server port 3000 busy | Another agent may be serving this repo; probe it and reuse if so. Otherwise start your own on a free port: npx vite --port 3101 |-| Playwright browser missing | npx playwright install chromium |-| A surface needs a signed-in user | Register a fresh account through the real /register flow against the real API and use it. Never mock the session. |-| A defect sits in code you did not touch | Fix it if it blocks a Definition of done line (root cause it, never mask it). Otherwise note it in the report and continue. |-| An unrelated test is red | Same rule. Never pipe npm test through tail; it masks exit codes. |--## Close out (required)--1. Verify every Definition of done line with the actual command output in- front of you. Never claim a line you did not verify.-2. Commit with explicit paths and a subject that describes the diff (house- style: type(scope): what changed and why a reader cares).-3. Delete this prompt file in that same commit:-- git rm prompts/swarm-100/api-tts-01.md-- The shrinking directory is this campaign's only progress ledger; there is- no progress log to update.-4. Final report: what step 0 measured, what changed (file list), evidence per- Definition of done line, and any one-line judgment calls. No trailing- questions, no unexecuted plans.--If a line genuinely cannot pass inside this session (an external party must-respond, or an owner-gated action is the final step), finish everything else,-leave this file in place, and state exactly which line remains and who owns-it. Never delete this file on a partial.diff --git a/tests/api/tts-input-guards.test.js b/tests/api/tts-input-guards.test.jsindex 15e0ac47d..34221c911 100644--- a/tests/api/tts-input-guards.test.js+++ b/tests/api/tts-input-guards.test.js@@ -390,6 +390,47 @@ describe('an unknown ElevenLabs voice is the caller\'s error, not the platform\'});});+describe('a key ElevenLabs rejects is reported as a key problem, not a gateway fault', () => {+ it('GET /api/tts/eleven/voices answers 401 invalid_key for a caller-supplied key', async () => {+ vi.resetModules();+ stubFetch({ elevenStatus: 401 });+ signIn();+ const res = await call('../../api/tts/eleven/voices.js', {+ method: 'GET',+ url: '/api/tts/eleven/voices',+ headers: { 'x-eleven-key': 'xi-a-key-this-account-revoked' },+ });+ expect(res.statusCode).toBe(401);+ expect(res.json().error).toBe('invalid_key');+ });++ it('GET /api/tts/eleven/voices keeps a genuine upstream fault at 502', async () => {+ vi.resetModules();+ stubFetch({ elevenStatus: 500 });+ signIn();+ const res = await call('../../api/tts/eleven/voices.js', {+ method: 'GET',+ url: '/api/tts/eleven/voices',+ headers: { 'x-eleven-key': 'xi-a-perfectly-good-key' },+ });+ expect(res.statusCode).toBe(502);+ expect(res.json().error).toBe('upstream_error');+ });++ it('GET /api/tts/eleven/library answers 401, the same way its own POST already did', async () => {+ vi.resetModules();+ stubFetch({ elevenStatus: 401 });+ signIn();+ const res = await call('../../api/tts/eleven/library.js', {+ method: 'GET',+ url: '/api/tts/eleven/library?q=news',+ headers: { 'x-eleven-key': 'xi-a-key-this-account-revoked' },+ });+ expect(res.statusCode).toBe(401);+ expect(res.json().error).toBe('invalid_key');+ });+});+describe('POST /api/tts/eleven-clone auth ordering', () => {it('answers 401 to a signed-out caller rather than reporting the key state', async () => {process.env.ELEVENLABS_API_KEY = 'xi-platform-key';