Dashboard sign-in
LiveEmail sign-in for operators. Session cookies gate projects and the upload UI.
Sign in →50% off · first 100
Ship Node.js voice and multiplayer apps. We run WebRTC, sessions, and infra.
Deploy voice agents and real-time multiplayer experiences without the WebRTC or session ops — we manage signaling, scaling, and infra. Ship agent logic and interactive sessions in TypeScript; optional local STT and TTS on every worker. Join the waitlist for early access on voicethere.io — the first 100 entries get 50% off.
Get early access
First 100 waitlist entries get 50% off when we open access.
Already shipping
Available today — dashboard, API, and CLI for the same projects and builds.
Dashboard sign-in via 3rd party
LiveSing in via GitHub, Google, or LinkedIn.
Projects & agent builds
LiveCreate projects, upload verified agent bundles, and inspect build history from the dashboard.
Open dashboard →Promote & rollback
LiveSet which build is active for a project or roll back to the previous release.
VoiceThere API
LiveREST at /api/v1 for projects, builds, promote, and rollback — same contract as the CLI.
API reference →CLI upload, deploy & promote
LivePublished @voicethere/cli — login, build upload, deploy --wait, and promote. Pair with @voicethere/agent verify in CI.
npm →Deploy to cloud
LiveRoll out your active build from the dashboard or CLI — voicethere deploy --wait promotes and provisions managed voice workers.
Voice sessions API
LiveStart a session from your backend; receive a join token and signaling URL for browser WebRTC. Async provisioning when workers scale up.
Dashboard chat & embed
LiveTest voice and text against echo agents from the project page, or paste an embed snippet with a client API key.
Team & access
LiveInvite teammates, assign org roles, and restrict projects to specific members from the dashboard.
Org audit log
LiveImmutable trail of API and dashboard actions — browse org-wide or per project.
Project usage metrics
LiveSession counts, billable minutes with monthly allowance progress, and error rate on each project.
Plans & subscriptions
LiveFlat monthly plans via Stripe Checkout and Customer Portal. Subscribe, assign subscriptions to projects, and buy multiple slots of the same tier.
View plans →Monthly usage allowances
LiveEach tier includes a monthly billable-minute allowance. Usage is tracked per project; new sessions are blocked at the limit, with grace before hard disconnect.
Session history & billing records
LivePaginated session list per project with status, duration, and billable seconds — same records as CLI sessions list and billing queries.
Multiplayer & data-only sessions
LiveSeveral clients in one session with shared or per-peer agents. Disable voice for DataChannel-only apps — games, live sync, and chat without STT/TTS.
Session & runner settings
LiveConfigure idle timeouts, data-only mode, shared vs per-peer agents, and cloud voice providers from the dashboard or CLI.
Session error tracking
LiveStructured errors from agents and workers in the dashboard — filter by session and map codes using the public error catalog.
Error catalog →Logging & session diagnostics
LiveWrite structured agent logs and search them in the dashboard — filter by message, level, and fields per project or session.
Developer docs (early)
LiveGetting started at /docs — agent environment, secrets, deploy flow, and session error reference. More topics rolling out before launch.
Open docs →Project Redis for shared agent state
LiveAdvanced and Ultimate projects get a private Redis instance for your agents — credentials injected at start. Sync game state, lobbies, and context across every concurrent session worker in the same project.
Advanced voice settings
LiveFine-tune STT/TTS, barge-in, and related voice behavior from the dashboard or API — beyond basic provider selection.
Public status page
LiveComponent health for voice and related services — operators and customers can check platform status.
Custom env & encrypted secrets
LiveSet custom environment variables and secrets for your agents — secrets are encrypted at rest and cannot be read back by the platform operator.
Developer packages
Install in your agent repo — build with @voicethere/agent, ship with @voicethere/cli, and connect browsers with @voicethere/client.
@voicethere/agent
Build and verify sandboxed agent bundles — defineAgent, speak, and speech events. Use before every upload.
npm →@voicethere/cli
voicethere login, projects, build upload, promote, and deploy --wait against the VoiceThere API.
npm →@voicethere/client
Browser and Node client for local dev and cloud voice sessions — connect, chat, and binary sync over WebRTC.
npm →Before public launch
Required for the initial public release — docs, embed polish, and operator-facing tooling.
Site embed widget
PlannedDashboard embed snippet works today; standalone npm package, theming, and one-line install polish before public launch.
Full developer documentation
PlannedComplete quickstart, API reference, browser client guide, and deploy runbooks at /docs.
Early docs →Managed TURN & ICE
PlannedRelay servers included in session mint responses — reliable calls through firewalls and NAT.
Cluster load computing
PlannedEnsure that every paid tier has guaranteed resources in the cluster, free tier can be queued or not available.
Newsletter & blog
PlannedProduct blog and email newsletter covering latest feature releases, guides, and platform updates.
Vendor-based concurrent connection limits
PlannedSet max concurrent sessions by STT/TTS choice — local/self-hosted voice uses more compute but costs less, so subscription tiers expose different concurrency caps than cloud vendors.
Customer-facing conversation history
PlannedBrowse past STT and TTS turns from the dashboard — stored encrypted, with PII masked where possible. Only speech recognition and synthesis events are logged; DataChannel messages are out of scope.
After v1
On the roadmap after the first public launch — multi-region, advanced voice ML, and deeper operator tooling.
Live session watch
PlannedReal-time event stream while a call is in progress — connect to the session websocket and receive events like agent speak, chat, and binary sync.
Team channels & room mixing
PlannedDynamic audio mix groups within a session — reassign who hears whom mid-call for team games and breakout voice.
Multi-region production
PlannedMulti-region EU, US, and APAC — regional deployments for a lower latency
Krisp voice model & recognition
PlannedOptional Krisp-powered turn-taking and interruption prediction for smoother conversations — enable when you need ML-grade voice activity and barge-in beyond the default energy VAD.
Multiple organisations per user
PlannedCreate and belong to more than one organisation, then switch between them from a dropdown in the dashboard.
Allowed agent npm packages
PlannedExpand the sandbox allowlist so agents can use selected LLM SDKs and other Node packages. Reach out and tell us which packages you need — we will add them to the whitelist or set up an npm install flow.
In-browser agent code editor
PlannedEdit agent code directly in the dashboard for quick fixes, with a validation flow that checks the new code still matches the defined agent protocol and expected behavior before you ship.
Built on open source
VoiceThere extends the node-webrtc-rust stack — develop locally, deploy the same agent bundle to our cloud.