Choose the architecture first: use ElevenAgents when ElevenLabs will host the agent and its conversational capabilities; use Speech Engine when your application supplies its own LLM and conversation logic. For a browser-based ElevenAgents assistant, the straightforward route is the official JavaScript client SDK, with a Node.js server issuing connection credentials for private agents. Keep the ElevenLabs API key on that server, not in browser code.
Choose between ElevenAgents and Speech Engine
These are two different ways to build a voice assistant, not interchangeable steps in one setup. ElevenAgents hosts the agent configuration and conversational capabilities. Speech Engine handles speech conversion and turn-taking while your server calls the LLM and controls the assistant’s replies.
As an Amazon Associate I earn from qualifying purchases.
| Decision | ElevenAgents | Speech Engine |
|---|---|---|
| Who supplies the LLM and conversation logic? | ElevenLabs hosts the agent platform and associated capabilities. | You supply the LLM and conversation logic. |
| What does your server do? | For a private agent, authenticate the app user and obtain connection credentials. | Receive transcript history, call your LLM, and stream response text back. |
| Best fit | You want to connect an application to a hosted conversational agent. | You want ElevenLabs speech capabilities around an existing or custom chat agent. |
If you choose ElevenAgents, the official JavaScript SDK defaults voice conversations to WebRTC and text-only conversations to WebSocket; you can also select a connection type explicitly. See the JavaScript SDK documentation. The sections below keep the hosted-agent and custom-LLM workflows separate.
The Tool Desk
Outbyte PC Repair FREEClear out junk files and repair common Windows errorsFree Scan →Outbyte Driver Updater FREEFix the driver behind crashes, sound loss and screen glitchesFind Drivers →Build a browser client for a hosted ElevenAgents agent
1. Create the agent and choose the client framework
Set up the agent in ElevenLabs first. The official Vite quickstart uses @elevenlabs/client; the Next.js quickstart uses @elevenlabs/react. Choose the example that matches your application rather than combining their package and setup instructions. Follow the relevant official guide: Vite quickstart or Next.js quickstart.
#1 Best Overall
- [Natural Audio Clarity] Operated with frequency response of 50Hz-16KHz, the podcasting XLR mic delivers balanced audio range, likely to resonate with your audience. Directional cardioid dynamic microphone corded will not exaggerate your voice, while rejects unwanted off-axis noise for vocal originality and intelligibility during your PS5 gaming streaming video recording. (Tips: Keep the top of end-addressing XLR dynamic microphone AM8 facing audio source, and suggested recording range is 2 to 6 in.)
- [XLR Connection Upgrade-Ability] To use XLR connection, connect the podcast microphone to an audio interface (or mixer) using a separate XLR cable (NOT Included) . Well-connected and smooth operation improves audio flexibility to make you explore various types of music recording singing. The streaming mic isolates the pristine and accurate sound from ambient noise with greater no interference and fidelity. (RGB and function key on mic are INACTIVE when using XLR connection.)
- [USB Connection with Handy Mute] Skip the hassle of setting something up and plug the cable to play the dynamic USB microphone directly, which suits for beginner creators or daily podcast. You can quickly control the gamer mic with tap-to-mute that is independent of computer/Macbook programs to keep privacy when live streaming. LED mute reminder helps you get rid of forgetting to cancel the mute. (RGB and function key are only available for USB connection, but NOT for XLR connection)
- [Soothing Controllable RGB] RGB ring on the desktop gaming microphone for PC, with 3 modes and more than 10 light colors collection, matches your PC gears accessories for gaming synergy even in dim room. You can control the RGB key button of the dynamic microphone USB directly for game color scheme gaming or live streaming. Configured memory function, the streaming microphone RGB no need to repeated selections after turnning off and brings itself alive when power on. (Only available for USB connection)
- [More Function Keys] Computer microphone with headphones jack upgrades your rhythm game experience and gets feedback whether the real-time voice your audience hear as expected. Get the desired level via monitoring volume control when gaming recording. Smooth mic gain knob on the PC microphone gaming has some resistance to the point, easily for audio attenuation or boost presence to less post-production audio. (Only available for USB connection)
2. Connect to a public or private agent
A public agent can be addressed with its agent ID using the documented conversation WebSocket endpoint: wss://api.elevenlabs.io/v1/convai/conversation?agent_id={agent_id}. For a private agent, the browser needs connection credentials issued by your server rather than direct access to your API key. The connection guide covers the signed-URL approach and the direct agent-ID flow.
3. Keep the API key on the server
Store ELEVENLABS_API_KEY in server-side configuration. Add an application route that verifies the signed-in user’s access, makes the authorized ElevenLabs request, and returns only the short-lived signed URL or conversation token needed by the client. Do not embed the API key in JavaScript sent to browsers: ElevenLabs explicitly warns, “Never expose your ElevenLabs API key on the client side.” Read the SDK guidance for private agents alongside the signed URL API reference.
Rank #2
- [Convenient Setup] Plug and play recording USB microphone for PC, with 5.9-Foot USB cable included for computer PC laptop, is connected directly to USB-A port for recording music, computer singing or podcast. The office condenser microphone for computer is easy to use and install. (NOT compatible with Xbox and Phones)
- [Durable Metal Design] Solid sturdy metal construction design, the computer microphone for Zoom meetings with stable tripod stand is convenient when you are doing voice overs or livestreams on YouTube. Durable material extends the service life of the voice-over microphone.
- [Mic Volume Knob] Gaming condenser USB mic compatible for PS4 with additional volume knob itself has a louder or quieter adjustment and is more sensitive. Your voice would be heard well enough through the zoom microphone USB when gaming, skyping or voice recording. Also, you can adjust your volume to zero and protect your privacy.
- [Widely Use] USB-powered design, the condenser microphone for recording no need the 48v Phantom power supply, works well with Cortana, Discord, voice chat and voice recognition. The podcast microphone for Mac, with USB-B to USB-A/C cable, is compatible with desktop, laptop or PS4/PS5, which meets most of your daily recording needs.
- [Clear Output Voice] Cardioid condenser microphone for PC captures your voice properly, producing clear smooth and crisp sound. Great computer recording mic for gamers/streamers/youtubers focus on the main source and reduces background noise. The streaming microphone does the job well for broadcast ,OBS and teamspeak.
4. Reflect conversation state in the application
Use the SDK’s lifecycle callbacks to represent connection, disconnection, incoming messages, and errors. A useful application state model lets the interface show whether the assistant is connecting or connected, renders user and agent messages, and surfaces errors to the user or logs. The Next.js guide demonstrates these callbacks.
Recommended Free Tools
When to use a direct Agents WebSocket
A low-level WebSocket client is an option when the application has a concrete need to control transport, audio capture, or protocol handling. For an ordinary browser integration, the official SDK is generally simpler; the direct route makes your application responsible for more protocol details.
Rank #3
- Custom three-capsule array: This professional USB mic produces clear, powerful, broadcast-quality sound for YouTube videos, Twitch game streaming, podcasting, Zoom meetings, music recording and more
- Blue VO!CE software: Elevate your streamings and recordings with clear broadcast vocal sound and entertain your audience with enhanced effects, advanced modulation and HD audio samples
- Four pickup patterns: Flexible cardioid, omni, bidirectional, and stereo pickup patterns allow you to record in ways that would normally require multiple mics, for vocals, instruments and podcasts
- Onboard audio controls: Headphone volume, pattern selection, instant mute, and mic gain put you in charge of every level of the audio recording and streaming process
- Positionable design: Pivot the mic in relation to the sound source to optimize your sound quality thanks to the adjustable desktop stand and track your voice in real time with no-latency monitoring
The documented flow connects to the conversation endpoint, initiates the conversation, sends microphone audio, processes returned events, and answers server ping events with pong according to the indicated delay. Consult the conversation API reference and WebSocket guide for the event format and lifecycle. The guide’s example audio-capture package is one implementation, not a hardware requirement.
- Handle connection setup and conversation initiation.
- Capture and send user audio, then process the agent’s returned messages and lifecycle events.
- Reply to ping events with pong on the server’s timing; do not assume an idle socket stays healthy without keep-alive handling.
Use Speech Engine for a custom LLM
With Speech Engine, ElevenLabs handles speech-to-text and text-to-speech, while your Node.js application receives transcript history, calls the LLM you choose, and streams response text back. The SDK handles turn-taking and interruption behavior. Its TypeScript integration can attach to an existing Node.js HTTP server or run as a standalone WebSocket server. See the Speech Engine overview and Node.js SDK reference.
Rank #4
- 360 Degree Position Adjustable Gooseneck Design --Plug and play USB microphone Pick up the sound from 360-degree with high sensitivity, in the best possible location for sound to your PC gaming, dragon voice dictation, and talk to Cortana
- Mute Button & LED Indicator --One-click to mute/unmute your microphone for pc, Build-in LED indicator tells you the working status at any time
- Intelligent Noise-Canceling Tech --Premium omnidirectional condenser microphone with noise-canceling technology can pick up your clear voice and reduce background noise and echo
- USB Plug&Play(1.8/6ft USB Cable) -- No driver required. Just need to plug & play for the microphone to start recording, well compatible with Windows(7, 8, 10 and 11) and macOS. (NOT compatible with Xbox/Raspberry Pi/Android)
- Solid Construction--Adopting premium metal pipe and heavy-duty ABS stand to make sure that you will be satisfied with our computer mic quality
Implement the transcript-to-response handler
In the SDK reference’s model, your onTranscript handler receives transcript messages with user and agent roles. Your server can pass the relevant history to its LLM, then send generated text back through session.sendResponse(...). Use the session’s cancellation signal where supported so a user interruption can stop an in-progress generation instead of allowing an obsolete answer to continue.
Quick wins for a faster PC:
Clear out junk files and repair common Windows errorsFree Scan →Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →Handle session initialization, close, disconnect, and error events in your server’s lifecycle logic. This is a server-owned conversation path: do not mix its transcript handler with the hosted ElevenAgents browser callbacks as though they were one integration.
Best Value
- 【Crystal Clear Audio Quality】Our Omnidirectional pattern condenser microphone accurately captures your voice, making it perfect for dictation, online classrooms, and more.
- 【Active Noise-Cancelling】Come in CMTECK CCS2.0 SMART CHIP with Omnidirectional Polar Pattern, which can effectively block the background noise. The pop filter prevents plosives from overloading the microphone, ensuring only your voice is heard.7
- 【Convenient Mute Button with LED Indicator】You can quickly mute/un-mute the microphone with the Mute Button and the built-in LED light lets you know the working status(Greenlight: Connected; Red light: Mute mode).
- 【Easy to use】 No drivers needed, just plug and record without external power supply, directly connect the microphone to a USB compatible device, well compatible with Windows(7, 8 and 10), Mac OS and PS4 (NOT compatible with Raspberry Pi/Linux/Android）
- 【Mini size with Adjustable Gooseneck】Adopted flexible and adjustable gooseneck metal pipe, easily adjust position 360 degrees to suit user comfort. The compact and stable base maximizes your desktop space.
Security and reliability checks
- Authenticate requests to your credential-issuing route before returning a private-agent signed URL or token.
- Avoid indiscriminate logging of signed URLs, tokens, or transcripts; set access and retention rules appropriate to your application.
- Make connect, disconnect, error, and interruption states observable in the interface or operational logs.
- For direct WebSocket clients, implement the documented ping/pong behavior.
- Do not treat the advanced multi-context WebSocket example as production-ready: ElevenLabs labels that example as not intended for production use. See the multi-context guide.
Practical build order
- Select the architecture: hosted ElevenAgents for a managed agent, or Speech Engine for your server’s custom LLM and conversation logic.
- Configure the agent or server: create the ElevenAgents agent, or prepare the Speech Engine handler and Node.js server integration.
- Connect the client: use the matching official Vite or Next.js SDK guide for ElevenAgents; for a private agent, have the server issue connection credentials.
- Wire conversation events: update the app from SDK callbacks, or handle WebSocket protocol events directly if you deliberately chose the low-level route.
- For Speech Engine, complete the turn handler: pass transcript history to your LLM, stream text responses, and honor cancellation on interruption.
Package names, connection defaults, and examples can change. Check the linked official documentation for the current instructions before implementing an integration.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
