Three recorded Lokutor API sessions illustrate a Spanish booking call, live switching among four languages, and a debate between two voice agents. Daniel Varela says the speech-to-text, language-model, and voice pipeline runs on CPU. The demonstrations show those interactions working in the sessions; they do not establish general latency guarantees or prove how the service performs against alternatives.
What the three sessions demonstrate
Booking a dental cleaning in Spanish
In the first session, one agent plays a caller and another a clinic receptionist. The caller asks to book a cleaning, is offered Thursday at 5:30 p.m. or Friday at 10 a.m., chooses Thursday, asks the price, and completes the booking at a quoted price of 45 euros. The session is described as lasting 40 seconds. The displayed per-turn latency readings are 207 ms, 206 ms, and 144 ms. Daniel Varela’s article presents this as a recorded demonstration, not a controlled test of booking accuracy across cases.
As an Amazon Associate I earn from qualifying purchases.
Switching among four languages
The second session uses the same agent and voice while switching live among Spanish, Catalan, Galician, and Basque. It is described as lasting 31 seconds. The displayed readings are 204 ms for Spanish, 144 ms for Catalan, and 67 ms for Galician; no reading is provided for Basque. The article also says the API handles English, Portuguese, French, Italian, and German, but the described session demonstrates only the four languages named above.
Free tools Windows power users keep installed
One-click scans. No signup required.
Two agents debating
In the third session, two Lokutor agents debate in Spanish and respond to one another. Its described duration is 36 seconds. The account illustrates agent-to-agent conversation but does not report a latency reading or a measure of debate quality.
#1 Best Overall
- Stay present in every scenario: Every conversation is covered, in person, on calls, and online. 4 MEMS + 1 VPU microphones with AI beamforming capture every voice across the room. Smart Dual-Mode Recording switches automatically between phone calls and in-person. The free Plaud Desktop captures online meetings without a bot
- Walk out of every meeting with notes ready to act on: Plaud Intelligence transcribes in 112 languages with speaker labels and turns each recording into action items, decisions, and follow-ups, structured and ready to use. Choose from 10,000+ customizable templates tailored to your role and industry
- AI summary ready before you reach your desk: Auto Transfer moves each recording to the Plaud app automatically, and AutoFlow transcribes and summarizes so your notes are ready before you are back at your desk. Upgrade anytime to Pro (1,200 min/mo) or Unlimited
- Access your AI workspace anywhere: One connected workspace across Plaud Desktop, Plaud Web, and the Plaud mobile app, so your conversations and finished work follow you everywhere
- Your conversations stay private and yours: Compliant with ISO 27001, ISO 27701, SOC 2, HIPAA, GDPR, and EN 18031, with zero data used to train AI models. Trusted by 2.5M+ professionals, including legal, medical, and business professionals handling sensitive information
How to interpret the latency figures
Varela defines the millisecond figure on screen as “measured server-side: first audio after end of turn detected.” In other words, the clock starts after the system detects that a speaker has finished and measures until the server produces the first audio. It is not a full end-to-end measure of how long a person waits from finishing a sentence to hearing a response: the stated boundary excludes the preceding turn and does not establish the contribution of network conditions or playback.
The readings are selected observations from the recorded sessions. The available account does not specify the hardware configuration, provide a sample-size analysis or repeatable latency distributions, or include an independent latency test or audio-quality evaluation. Treat the numbers as reported demonstration results, not as typical performance, a service-level guarantee, or a basis for ranking Lokutor against another API.
Rank #2
- YOUR AI PERSONAL ASSISTANT FOR EVERYDAY PRODUCTIVITY: More than a voice recorder, Pocket works as your AI personal assistant to capture, transcribe, and summarize meetings, calls, and ideas instantly. Core features are included out of the box, with optional advanced tools available for power users.
- ONE-TAP RECORDING FOR REAL-LIFE MOMENTS: Capture meetings, phone calls, and in-person conversations instantly with a simple tap, no typing, no interruptions, just effortless note-taking anywhere you go.
- SMART AI INSIGHTS & ORGANIZATION: Pocket automatically turns recordings into clear summaries, key action items and structured conversation maps so you can quickly review what matters without digging through audio.
- TURN CONVERSATIONS INTO ACTION WITH “ASK POCKET”: Don’t just record, understand. Instantly ask questions across your meetings, extract key insights and generate next steps in seconds. All grounded in your recordings, so answers stay accurate and reliable.
- MAGSAFE COMPATIBLE FOR SEAMLESS USE: Easily attach Pocket to your iPhone or other MagSafe compatible devices for convenient, hands-free recording on the go. Perfect for capturing meetings, calls, and ideas without needing to hold your device.
What the demonstrations do not establish
- General performance: Three sessions cannot show how latency or task completion varies across users, prompts, network conditions, or repeated runs.
- CPU requirements or deployment details: The author says speech-to-text, the LLM, and voice run on CPU, but the available account gives no hardware configuration or deployment requirements.
- Current product terms: The article identifies Lokutor and points readers toward an API key and documentation, but does not establish current availability, pricing, or terms.
- Comparative standing: No alternatives are tested, so the sessions do not support a claim that Lokutor is faster or better than other voice-agent APIs.
What to check when evaluating a voice-agent API
Use these sessions as examples of the kinds of workflows a voice agent can demonstrate, not as a procurement benchmark. For a meaningful comparison, look for:
- Task completion quality across representative conversations, including errors and recovery.
- Which languages and voices are supported in practice, rather than only named in a product description.
- The measurement boundary: when latency starts and ends, and whether it includes turn detection, network transit, and audio playback.
- Hardware and runtime configuration, plus repeated tests that report latency distributions rather than a few selected readings.
Varela’s article is titled “Three real sessions on a CPU voice agent API” and invites readers to “Run it yourself.” Its linked API-key and documentation destinations may help readers explore the service, but the available information here does not verify whether those endpoints or the service remain current.
Quick Recap
Best Value
- AI-POWERED TRANSCRIPTION & SUMMARIES: Plaud Note Pro is your professional voice transcriber, delivering high-accuracy transcription in 112 languages with auto speaker labels. Powered by top AI models and thousands of templates, Note Pro instantly creates structured summaries, mind maps, To-Do lists, and proposals tailored to your role and industry
- ENHANCED CONTEXT WITH MULTIMODAL INPUT: Capture audio, type notes, add images, and press to highlight key moments for richer context. During recording, instantly mark key moments with a single button press. Simultaneously enrich your audio by snapping photos of important documents or typing in ideas
- CHAT WITH YOUR RECORDINGS USING "ASK Plaud": Unlock deeper insights with this interactive AI. Ask questions, extract key points, draft emails, and get next-step suggestions—all grounded in your original audio for reliable, ready-to-use answers
- INTELLIGENT RECORDING WITH AI DIRECTIONAL AUDIO: Enjoy seamless, intelligent recording with Plaud Note Pro. Its AI automatically switches between call and meeting modes while recording, while directional audio and real-time spatial awareness minimize noise to capture voices with crystal clarity
- Everything Included: Includes Plaud Note Pro, magnetic case, magnetic ring, charging cable, and a free Starter Plan with 300 transcription minutes per month. Upgrade anytime in the Plaud app to Pro Plan (1,200 min/mo) or Unlimited Plan(Up to 24 hours of transcription per user per day)
Rank #4
- YOUR AI PERSONAL ASSISTANT FOR EVERYDAY PRODUCTIVITY: More than a voice recorder, Pocket works as your AI personal assistant to capture, transcribe, and summarize meetings, calls, and ideas instantly. Core features are included out of the box, with optional advanced tools available for power users.
- ONE-TAP RECORDING FOR REAL-LIFE MOMENTS: Capture meetings, phone calls, and in-person conversations instantly with a simple tap, no typing, no interruptions, just effortless note-taking anywhere you go.
- SMART AI INSIGHTS & ORGANIZATION: Pocket automatically turns recordings into clear summaries, key action items and structured conversation maps so you can quickly review what matters without digging through audio.
- TURN CONVERSATIONS INTO ACTION WITH “ASK POCKET”: Don’t just record, understand. Instantly ask questions across your meetings, extract key insights and generate next steps in seconds. All grounded in your recordings, so answers stay accurate and reliable.
- MAGSAFE COMPATIBLE FOR SEAMLESS USE: Easily attach Pocket to your iPhone or other MagSafe compatible devices for convenient, hands-free recording on the go. Perfect for capturing meetings, calls, and ideas without needing to hold your device.
Rank #3
- YOUR AI PERSONAL ASSISTANT FOR EVERYDAY PRODUCTIVITY: More than a voice recorder, Pocket works as your AI personal assistant to capture, transcribe, and summarize meetings, calls, and ideas instantly. Core features are included out of the box, with optional advanced tools available for power users.
- ONE-TAP RECORDING FOR REAL-LIFE MOMENTS: Capture meetings, phone calls, and in-person conversations instantly with a simple tap, no typing, no interruptions, just effortless note-taking anywhere you go.
- SMART AI INSIGHTS & ORGANIZATION: Pocket automatically turns recordings into clear summaries, key action items and structured conversation maps so you can quickly review what matters without digging through audio.
- TURN CONVERSATIONS INTO ACTION WITH “ASK POCKET”: Don’t just record, understand. Instantly ask questions across your meetings, extract key insights and generate next steps in seconds. All grounded in your recordings, so answers stay accurate and reliable.
- MAGSAFE COMPATIBLE FOR SEAMLESS USE: Easily attach Pocket to your iPhone or other MagSafe compatible devices for convenient, hands-free recording on the go. Perfect for capturing meetings, calls, and ideas without needing to hold your device.
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.
