It's time to talk to your Clawdbot. ClawdTalk gives your agent a phone number so you can call, text or WhatsApp it from anywhere in the world. ClawdTalk is voice-first, so you can have actual conversations instead of being confined to chat windows. It's secure by design, your agent can only call and text you, and it's easy to set up, just add your phone number and start talking. Start free with 10 minutes of voice and 10 messages per day. Your Clawdbot, reachable anywhere. Powered by Telnyx.
Hi PH 👋
Telnyx is the infrastructure for Agents, and ClawdTalk is the fastest way to give your Clawdbot a voice.
Your agent gets a real phone number so you can talk, text, and WhatsApp your bot wherever you are in the world, no terminal or bulky UI needed.
Try it out for free and let us know what you think!
This is great! But could you please enable international outbound calls/text? My bot says its restricted to US numbers while we are located in Europe, so that makes it kind of useless.
Awesome concept, such a bummer though that there are only US voices. Are there any UK voices in the Pipeline?
I have a use-case which am working with community to call up friends and family based on a certain trigger, i dont see this is working with openclaw, can you include more documentation please, below are my logs. I have tried in both cloud-instance and also on the Telegram chat
-Rakesh
Hold up. ✋🛑
clawdhub is not a valid command.
If you are trying to install a new skill/plugin, the command structure is usually handled via npm or manual installation for OpenClaw.
However, if you are referring to a custom tool or script you found, I need to know how you want me to install it.
Usually, I would:
1. git clone the repo.
2. npm install.
3. Add it to my skill config.
Can you clarify the source? Or did you mean to run this command yourself on the host? 🤔
Tested it out, really neat stuff. Hoping eleven labs voices will be added, as well as conferencing.
“Infrastructure for agents” is a strong positioning. In early usage, what teams found most valuable, provisioning communication instantly through APIs or having voice, messaging, and compute unified in one stack?
Feature request: if we whitelist our personal phone number, can we skip needing to enter the PIN? Otherwise, looks like SMS handler isn't pushing events through properly / not getting anything via the websocket. The Discord invite in the app is also stale.
Environment:
clawdtalk-client v1.2.9
OpenClaw gateway on macOS (arm64)
Node v25.6.0
Issue: WebSocket connection authenticates successfully and voice calls route correctly via "deep tool" requests. However, inbound SMS messages are not being pushed through the WebSocket.
The client has an sms.received event handler at line 406 of ws-client.js:
if (event === 'sms.received') {
this.handleInboundSms(smsFrom, smsBody, messageId);
}
But no sms.received events arrive over the socket. SMS messages exist on the server (confirmed via sms.sh list), they're just not being pushed to connected clients.
Expected behavior: Inbound SMS should trigger sms.received WebSocket events, same as voice calls trigger call.started / transcription events.
No SMS events follow, despite messages received during the session.
Workaround: Currently polling via sms.sh list, but real-time routing would match the voice experience.
Voice-first approach for AI agents is a natural evolution from terminal and chat interfaces. The whitelist-based security model seems well-designed for preventing unauthorized access. Curious about the session state management - if a voice call gets disconnected mid-conversation, does the agent preserve context for when the user calls back, or does it require a fresh start?
Voice-first is def the right call (pun intended). This is huge for accessibility as well! It means people who struggle with text interfaces finally get a way to interact with AI agents.
Wow, Telnyx is seriously cool! Love the concept of agents directly managing comms. Curious how ClawdTalk handles potential abuse or spam calls with that direct number access?
Is the number provided with for the paid Starter package a cell number that would also work with WhatsApp business? If so what country is the number based?
The ~1200ms latency because you own the telco layer is the real differentiator here - most voice AI feels robotic because of those extra network hops. Giving agents actual phone numbers opens up so many use cases beyond web chat. Curious about how the voice providers (Rime/Minimax/Resemble) compare in real-world conversations - any noticeable differences in handling interruptions or speaking pace?
Looks great, would be fun to have a voice on my buddy client.. Is this supports only english or are there any other language options?
what is the latency for whole cycle? it will be really cool if it is around 1200 ms.
Woah, is there any option to set up specific/customized voice or it sets it up itself?
