Blog
Release notes, platform updates, and product news from the VoiceThere team.
October 21, 2026 · release
VoiceThere 0.3.0
Speech on dedicated servers with faster, more accurate replies under load, language switching mid-call, calls that survive network drops, deploy history and a redesigned dashboard.
@voicethere/agent 0.10.0 · @voicethere/cli 0.16.9 · @voicethere/client 0.11.9
October 20, 2026 · release
One request shape for every speech provider
The built-in speech is now called voicethere, and setVoiceLanguage takes the same request for VoiceThere and every cloud vendor, with error messages that say what to change.
@voicethere/agent 0.10.0 · @voicethere/cli 0.16.9
October 20, 2026 · platform
Speech latency numbers, published
Median and p90 latency for VoiceThere speech and five cloud speech vendors, with the method and the commands to repeat it.
node-webrtc-rust 0.12.1 · @voicethere/client
October 19, 2026 · platform
See which voice answered each turn
Every caller and agent row in the session timeline now has an ⓘ with the model or voice, the timings and an estimated credit cost.
October 19, 2026 · platform
Load testing VoiceThere: 45 voice conversations, measured
Detailed results of our voice load tests: 45 conversations at once, capacity per pair of speech servers, and where the wait between the end of a sentence and the agent's answer comes from.
October 18, 2026 · platform
Deploys now say why they failed
A failed deploy tells you whether to fix your agent or wait for us, and a failure on our side comes with a ticket button.
October 17, 2026 · release
Fish Audio Drama 3 for voice agents
Pick Fish Audio for TTS with Drama 3, for STT with transcribe-1, or both, using your own Fish key.
October 16, 2026 · release
Force deploys for urgent fixes
Deploying in Force mode now ends calls on the old version within 15 seconds of the new version being ready, while Drain works as before.
October 16, 2026 · platform
Voice replies start sooner after a period
Voice agents now capitalize the first letter after a sentence end in the text sent to the voice engine, so the engine splits sentences there. A project setting turns it off.
October 13, 2026 · release
Every agent template, straight from @voicethere/agent
The create-project picker now lists every template in the current @voicethere/agent release, including language switch and inbound webhooks.
@voicethere/agent 0.9.8 · @voicethere/cli 0.16.2
October 13, 2026 · platform
Language switches get a second try
A slow language start is announced to the caller, retried once, and a language that still cannot start is reported instead of being misheard.
October 10, 2026 · release
See which voice used your characters
The project Usage page now breaks speech usage down by voice, with characters, credits and sessions per voice.
October 9, 2026 · release
From a metrics chart to the exact sessions and logs
Failures by reason and top errors in project metrics now open the sessions and logs behind them, and the CLI can read metrics and apply the same filters.
@voicethere/cli 0.16.0
October 8, 2026 · platform
Project metrics: see how your agent performs
A new Metrics area with Overview, Sessions, Voice and Agent tabs, plus a separate Usage page for credits.
October 8, 2026 · release
Short network drops no longer end a voice conversation
@voicethere/client 0.11.6 rides out short network drops, the reconnect window is a project setting, and replies wait for a busy speech server instead of dropping the call.
@voicethere/client 0.11.6
October 6, 2026 · platform
Repeated replies now play from memory, free of charge
Voice agents replay repeated TTS replies from memory, those replays are not billed, and a project setting lets you turn the cache off.
October 5, 2026 · release
Language switches without interrupting the caller
Automatic language switches now wait for the caller to finish, say a short ready message after a slow switch, and need VoiceThere speech on both sides.
September 30, 2026 · platform
New guide: pauses and pronunciation for VoiceThere voices
We added documentation on shaping how VoiceThere voices speak your agent's text.
September 29, 2026 · release
Mid-conversation language switch for voice agents
setVoiceLanguage keeps WebRTC up while STT/TTS follow the caller; optional LID auto-switch and per-language presets are off by default.
@voicethere/agent
September 28, 2026 · release
Expanded cloud STT and TTS vendors
Configure Deepgram TTS, ElevenLabs Scribe, Groq, Azure Speech, and AWS alongside existing vendors, with per-vendor setup docs and project secrets.
September 26, 2026 · release
Spatial soundboard: stable ids per placed sound
Each sound on the showcase stage keeps a short id so Stop targets one instance, including when loops restart.
September 25, 2026 · release
Key-only embed bootstrap for @voicethere/client
The embed client resolves project identity and widget appearance from your client API key alone — available in @voicethere/client 0.9.0.
@voicethere/client 0.9.0
September 24, 2026 · release
Disable conversation history while collecting sensitive speech
Pause STT/TTS transcript storage for one session so a PIN, password, or card number is not written to the Conversation tab.
@voicethere/agent
September 23, 2026 · platform
LLM index lists shipped features and speech prices
/llms.txt and /llms-full.txt now catalog deployed VoiceThere features, on-platform STT and TTS, and plan prices.
September 22, 2026 · release
VoiceThere 0.2.0
Dashboard Code tab, spatial audio, spoken language ID, embed widget designer, spoken chat stream, and npm packages for agent authors.
@voicethere/agent 0.8.1 · @voicethere/cli 0.14.5 · @voicethere/client 0.8.3 · @node-webrtc-rust/sdk 0.9.10
September 21, 2026 · platform
Docs for every public VoiceThere npm package
Developer docs now group @voicethere/agent, CLI, client, and the open WebRTC SDK under their own npm packages section.
@voicethere/agent 0.8.1 · @voicethere/cli 0.14.5 · @voicethere/client 0.8.3
September 21, 2026 · release
Spoken text streams into the embed chat
Turn on streamSpokenText so agent speech appears word by word in the widget chat while audio plays.
September 21, 2026 · release
Download project source and builds from the dashboard
Save a zip of your workspace or grab agent.js from the Code tab or Overview build history.
September 21, 2026 · release
Code tab: compile, promote, and deploy as separate steps
On the Code tab, compile stores a build, promote makes it active, and deploy rolls it out.
@voicethere/agent · @voicethere/cli
September 19, 2026 · release
Embed widget styler: live preview chat, positions, and custom CSS
Style the site embed from the dashboard — connect in preview, hide the pill when open, more corners, fonts, and scoped custom CSS.
@voicethere/client 0.8.2
September 19, 2026 · platform
Landing Voice+Data mix example
The homepage How it works panel now shows multi-client positional mix and links each flow to the docs.
September 19, 2026 · release
Data-only world sync from JSON to ArrayBuffers
New docs and agent templates for syncing positions over a WebRTC data channel — JSON, binary ArrayBuffers, and Redis.
@voicethere/agent 0.8.0
September 15, 2026 · release
Agent 0.7.11 and CLI 0.14.1 patch releases
Spatial-showcase emits pose before the first TTS chunk; deploy --wait timeouts include the last job error.
@voicethere/agent 0.7.11 · @voicethere/cli 0.14.1
September 14, 2026 · platform
Spatial audio showcases: orbit, soundboard, proximity
Three live demos on the marketing site let visitors hear positional TTS, panned clips, and proximity room mix in stereo headphones.
@voicethere/agent 0.7.10
September 11, 2026 · release
LLM agent discovery with /llms.txt
VoiceThere publishes spec-compliant /llms.txt so coding agents find docs, OpenAPI, sessions, webhooks, and npm packages.
September 10, 2026 · platform
Tune spoken language identification from the dashboard
Enable or disable Whisper LID and set minSpeechMs (1000–5000 ms, default 2500) per project.
September 10, 2026 · release
Template workspaces now include package.json
Seeded agent templates load a root npm package.json in the Code tab; older projects can add one with a single click.
@voicethere/agent 0.7.8
September 9, 2026 · release
Higher code editor source size limits
Subscription tiers now allow more UTF-8 source in the dashboard Code tab before save or compile rejects the tree.
September 9, 2026 · release
Code editor: agent SDK and Node IntelliSense by default
The dashboard Code tab loads @voicethere/agent and Node typings as soon as you open the editor, with no typecheck job required.
@voicethere/agent
September 8, 2026 · release
Higher code editor typings pack limits
Subscription tiers now allow larger .d.ts JSON packs after typecheck/compile so the dashboard Code tab can IntelliSense more npm dependencies.
September 7, 2026 · release
Spoken language identification for voice agents
Detect the caller’s spoken language and handle user_language events to route prompts and TTS.
@voicethere/agent
September 7, 2026 · release
Mute, mix status, and STT in positional mix
Global and per-listener mute, mix status introspection, and STT overrides join positional mix groups and per-client TTS poses in @voicethere/agent 0.7.1.
@voicethere/agent 0.7.1
September 7, 2026 · release
Clip playback for voice agents
Play HTTPS audio clips or small inline bytes to one or all voice clients, with play-id progress and stop control in @voicethere/agent.
@voicethere/agent
September 2, 2026 · release
Positional mix and orbiting TTS
Voice+Data mix groups, live stereo poses, and per-client TTS orbits in @voicethere/agent.
@voicethere/agent
September 1, 2026 · release
Inbound RNNoise on by default for voice runners
Voice and Voice+Data projects now enable inbound noise suppression by default; turn it off per project when CPU is tight.
August 31, 2026 · release
Recording-consent agent template
Starter agent that asks recording consent on session connect, pauses around name and birthdate, and respects project recording settings.
@voicethere/agent 0.5.6
August 31, 2026 · release
Dashboard code editor for agent source
Edit, typecheck, compile, and deploy agent TypeScript from the project Code tab. Public npm semver deps are always on, with per-plan source size limits.
@voicethere/agent 0.5.6
August 31, 2026 · release
@voicethere/client 0.8.0: async embed with CDN configUrl
Access embed snippets now use createVoiceThereWidgetAsync with optional configUrl so launcher appearance updates after Deploy without editing host HTML.
@voicethere/client 0.8.0
August 30, 2026 · release
CLI deploy wait timeouts show last job status
When deploy --wait times out, the CLI now prints whether the job was still queued, already active, or never polled.
@voicethere/cli 0.12.8
August 30, 2026 · release
Embed widget designer and CDN-published appearance
Style the floating launcher from a dedicated Widget tab. Deploy publishes appearance JSON on the VoiceThere CDN without exposing your client API key.
@voicethere/client 0.7.29
August 30, 2026 · release
@voicethere/agent 0.5.5: game-sync remove by id
game-sync removes a specific object by id, keeps the Redis world running with no clients, plus voice-showcase weather ZIP and ioredis test-flake fixes.
@voicethere/agent 0.5.5
August 29, 2026 · release
VoiceThere 0.1.0 — production platform roundup
Self-serve signup, metered billing opt-in, conversation recording, inbound webhooks, and a full dashboard polish pass — now on app.voicethere.io.
@voicethere/agent 0.5.1 · @voicethere/cli 0.12.7
August 29, 2026 · release
Metered usage is now opt-in
On-demand metered billing defaults off until you add a payment method and enable it in billing settings.
August 28, 2026 · release
Voice showcase template and shared-world spawn cap
New conversational agent template docs and a 25-object cap with Remove on the marketing shared-world board.
@voicethere/agent 0.5.4
August 28, 2026 · release
Project Usage tab on the dashboard
The project Metrics tab is now labeled Usage so credit consumption and session stats are easier to find.
August 28, 2026 · release
Clearer mic-denied notices in embed and dashboard chat
Voice chat now explains when the microphone is blocked in nested iframes, keeps agent audio when playback is allowed, and offers Enable sound when autoplay is blocked.
@voicethere/client 0.7.29
August 27, 2026 · release
Live showcase demos on the marketing site
Try voice and multiplayer examples from the home page and /showcase without signing up first.
August 27, 2026 · release
Voice metrics on the project dashboard
See STT/TTS p50, p95, and p99 latency, utterance volume, barge-in rate, and VAD transitions scoped to each project.
August 27, 2026 · release
Fractional credits for conversation recording overage
Metered recording overage now bills by actual duration (seconds ÷ 60), not rounded-up whole minutes.
August 26, 2026 · release
Usage statements and Stripe invoices
Printable credit breakdowns by project and kind, plus hosted Stripe invoice links for cash billing.
August 26, 2026 · release
Agent log overage settles to usage credits
Paid projects with agent log overage enabled now debit usage credits for log entries past the monthly included cap.
August 26, 2026 · release
@voicethere/agent 0.5.1 — verify webhook and session-start agents
Agent verify and dashboard upload now accept bundles with only onWebhook or onSessionStart — no speech or DataChannel handlers required.
@voicethere/agent 0.5.1
August 25, 2026 · release
Inbound webhooks for agent HTTP ingress
Advanced and Ultimate projects can POST HTTPS webhooks that fan out to every ready session worker — verify payloads in your agent.
August 25, 2026 · release
Docs search and grouped guides
Search developer documentation by keyword and browse guides grouped under Guides and Help on /docs.
August 25, 2026 · release
Cloud rollout redeploy hint
The dashboard warns when runner settings changed after your last cloud deploy.
August 25, 2026 · release
Quieter CLI settings updates
projects settings set and related commands now print only the key you changed.
@voicethere/cli 0.12.4
August 23, 2026 · release
Conversation recording with agent pause and resume
Opt-in voice-session audio, dashboard playback, CLI download, included minutes per plan, and agent controls for consent and sensitive segments.
@voicethere/agent 0.4.0 · @voicethere/cli 0.12.1
August 22, 2026 · platform
Open self-serve signup
Create a VoiceThere account from the landing page — no waitlist. Operators can still reach historical waitlist contacts from admin newsletters.
August 21, 2026 · release
Metered usage now requires a payment method
On-demand metered billing stays off until your organization adds a card, with per-project toggles and org-first spend caps.
August 21, 2026 · platform
Per-project browser CORS origins
Allow your production and pre-production sites to call the sessions API from the browser — configure origins on the project Access page.
August 21, 2026 · release
August platform update: browser origins, safer projects, clearer voice docs
Configure which sites can call your sessions API from the browser, safer project admin and delete flows, and clearer voice vendor docs.
August 13, 2026 · platform
Expanded developer documentation
New guides for quickstart, agent templates, runner settings, session idle timeout, and conversation history — all linked from the docs index.
August 1, 2026 · news
VoiceThere blog launches
Release notes, platform updates, and product news now live on the VoiceThere blog.
July 28, 2026 · platform
Dashboard and session diagnostics
Project metrics, session detail usage panels, and clearer billing breakdowns on the VoiceThere dashboard.
July 15, 2026 · release
Client, agent, and CLI npm releases
New @voicethere/client, @voicethere/agent, and @voicethere/cli releases with improved session lifecycle and deploy workflows.
@voicethere/client 0.7.23 · @voicethere/agent 0.3.0 · @voicethere/cli 0.2.4