We’ve already discussed the challenges of turn-taking in conversational AI in this blog post.
Now, we’re excited to announce our newest Turn-Taking model, available as part of Krisp’s VIVA SDK.

In this article, we’ll walk through the technology behind the new model and share our latest testing results. The new generation of models is more streamlined than ever—making it simple to integrate Voice Isolation, Turn-Taking, and VAD into your Voice AI pipelines.

If you’d like to see how Krisp’s VIVA SDK can enhance your Voice AI agent experience, apply now from our Developers page.

How the New Model Works

Our latest model predicts End-of-Turns using only audio input—perfect for real-time conversational systems like human-bot interactions.

Compared to v1, krisp-viva-tt-v2 represents a major step forward. It was trained on a more diverse and better-structured dataset, with richer data augmentations that help the model perform more reliably in real-world conditions.

Key Improvements in v2

• Greater robustness in noisy environments
• Higher accuracy when paired with Krisp’s Voice Isolation models
• Faster and more stable turn detection in live conversations

Testing Results

Testing on Clean Audio

We evaluated both model versions on ~1800 audio samples from real conversations, including ~1000 “hold” cases and ~800 “shift” cases, with mild background noise.

Although the numerical difference between versions is small on this clean dataset, the results show that v2 achieves faster mean shift prediction time at the same false positive rate.

Insight: Even in clean audio conditions, krisp-viva-tt-v2 offers slightly better prediction stability and overall performance.

Testing on Noisy Audio

Next, we evaluated the models on noisy audio mixes at 5 dB, 10 dB, and 15 dB noise levels. Two scenarios were tested:

1. Directly on the noisy dataset
2. On the same dataset after processing through the Krisp VIVA Voice Isolation model

In both scenarios, krisp-viva-tt-v2 consistently outperformed v1.

Insight: krisp-viva-tt-v2 delivers up to a 6% improvement in F1 score under noisy conditions, demonstrating greater resilience in real-world environments.

Testing After Noise and Voice Removal

Finally, we tested both models on the same noisy dataset after applying background noise and voice removal with the krisp-viva-tel-v2 model.

Insight: When combined with Krisp’s Voice Isolation technology, v2 achieves even greater accuracy and stability.

Conclusion

The new krisp-viva-tt-v2 model marks a significant leap forward in real-time conversation handling for Voice AI. With improved robustness against noise and smoother integration with Krisp’s other models, developers can now build faster, smarter, and more natural-sounding conversational agents.

Explore the VIVA SDK today and see how Krisp’s advanced models can elevate your Voice AI experience.

The post Audio-Only Turn-Taking Model v2 appeared first on Krisp.

Durban, South Africa — October 16, 2025 — Krisp, the leader in real-time voice AI technology, today announced the launch of Accent Conversion for Africa, enabling clearer and more natural conversations across the country’s customer experience (CX) sector. As one of the world’s fastest-emerging outsourcing hubs, Africa has a highly skilled, English-speaking workforce with strong cultural alignment to Western markets, positioning it as a strategic bridge for CX operations across Africa and Europe. Krisp Accent Conversion for Africa supports African English accents, including South African, Ugandan, Kenyan, and Nigerian. 

The launch builds on the success of Krisp Accent Conversion 3.7, which supports Indian, Pakistani, Filipino, and Latin American English accents. Powering CX operations at tier-1 banks, insurers, and BPOs worldwide, Krisp’s AI-powered solution continues to set the industry benchmark for speech clarity, phoneme precision, and naturalness. Krisp Accent Conversion for Africa delivers near-native comprehension between contact center agents and consumers, demonstrating a higher performance than both competitors and unprocessed voice.

“Even in the age of AI, human agents are at the front lines of every meaningful customer interaction and they deserve to be clearly understood,” said Davit Baghdasaryan, Co-Founder and CEO of Krisp. “As the CX industry evolves to become more AI-driven, one thing remains constant: human connection drives loyalty and trust. With Krisp, clarity becomes universal, not cultural, by removing accent bias and empowering every voice to connect globally.”

Advantages of Krisp Accent Conversion for Africa include:

• Proven performance + measurable impact: Krisp is already trusted at scale, with 250,000+ enterprise seats deployed and 80B+ minutes processed monthly in real-time conversations. Customers using Krisp have seen +99% NPS from end-customers.
• Eliminated accent bias: Krisp bridges clarity gaps across Africa’s diverse English accents and native languages.
• Talent expansion + boosted retention: Krisp accent conversion expands access to CX jobs for agents who might otherwise be excluded and preserves agents’ authentic voices, building confidence and authenticity.
• Cutting costs: Removes the need for expensive and limiting accent neutralization training.
• Global competitiveness: Allows operators to hire broadly, without limitations due to accent, and compete more effectively with leading outsourcing hubs like India and the Philippines.

“By integrating Krisp’s AI platform, including Accent Conversion and noise cancellation, we’re amplifying the human touch at every interaction,” said Sudhir Agarwal, Founder & CEO of Everise. “Krisp’s technology has consistently outperformed in head-to-head evaluations across clarity, naturalness, and accent accuracy.”

Krisp’s mission is to enhance the productivity of every voice interaction, which includes eliminating bias and language barriers. By combining advanced voice AI with enterprise-scale reliability, Krisp enables global CX organizations to deliver consistent, high-quality interactions at every touchpoint. 

To learn more, visit https://krisp.ai/contact-center/accent-conversion/

Media Contact

Molly Leahy

krispPR@walkersands.com

The post Krisp Launches Accent Conversion for Africa appeared first on Krisp.

You’d have Zoom open in one window, your notes app in another, and your agenda in a third. Every time you switched screens, you risked missing something important.

Companion Mode Fixes That

Krisp Companion Mode creates a dedicated meeting space right inside Krisp. It’s your calm center, where you can see your agenda, capture personal notes, track recordings, and manage controls without leaving the conversation.

Now, it also helps you follow every word with Live Transcription in 16 languages. This helps you stay fully engaged and never miss a detail.

What You Can Do Today That You Couldn’t Before

• Manage everything in one view: Your agenda, personal notes, transcription, and controls now live in a single panel.
• Stay focused: Companion Mode launches automatically when you join a meeting or start recording.
• Take better notes: Jot down insights in real time while Krisp captures the full transcript. Add personal context that AI alone can’t.
• Follow every word: Turn on Live Transcription with the CC button, choose your language, and see the conversation unfold as it happens.
• Jump back into calls instantly: A Meeting in Progress banner keeps you one click away from active meetings.
• You + AI = Better Together: After the meeting, Krisp enhances your notes with AI-generated summaries, making follow-ups effortless.

(Live Transcription available for Pro and Business users.)

How It Changes Your Workflow

Here’s how most people manage calls today:

• Open Zoom or Google Meet
• Open notes in a separate app
• Switch tabs to find the agenda
• Miss key discussion points in the process

With Companion Mode:

• Join the meeting directly from Krisp
• See your agenda, notes, transcription, and controls in one panel
• Capture insights live and review AI summaries after

The result: less stress, better focus, and nothing missed.

The post Introducing Krisp Companion Mode: Stay Present in Every Meeting appeared first on Krisp.

With Krisp Desktop 2.0, that’s over. The dashboard you knew is now a full-featured control center. Join calls, manage recordings, mute background noise, review your agenda, and start in-person sessions

What You Can Do Today That You Couldn’t Before

• Control your meetings in one place: Start recordings, mute noise, send the AI note-taker bot, and join meetings without leaving Krisp.
• Join calls instantly: The Active Call Banner keeps you one click away from recording, managing, or rejoining meetings.
• Stay organized: Switch to collapsed mode for a minimal view when you want fewer distractions.
• Access your agenda effortlessly: Your upcoming calls are right inside Krisp. Join directly or start an in-person session instantly.
• Resize your workspace: Make Krisp as big or compact as you want. The dashboard adapts seamlessly.

How It Changes Your Workflow

Let’s say you have three calls back-to-back:

Before Desktop 2.0:

• Check your calendar for the meeting link
• Open Zoom or Teams
• Switch to Krisp to enable noise cancellation
• Open notes in another app

With Desktop 2.0:

• Open Krisp Desktop
• Join the meeting from your Upcoming (previously agenda) page
• Jump in from a notification Krisp sends when your meeting starts
• Noise cancellation starts automatically
• Manage recordings, notes, and controls right from the same screen

One app. One flow. More focus.

The post Your New Meeting Control Center: Krisp Desktop 2.0 appeared first on Krisp.

In May 2025, we released Accent Conversion v3.5, bringing a major quality upgrade — with ~20% improvement across key metrics for both Filipino and Indian accents (details here). Thanks to Krisp desktop application’s auto-update mechanism, the rollout reached 95% of users within 2 days, and the feedback was overwhelmingly positive, both from agents and customers, driving sentiment and business KPIs.

In July 2025, we expanded the offering to support the Latin American accent pack. The launch quickly gained traction with several large customers and is now deployed across thousands of agents.

Throughout this period, we’ve worked closely with partners, agents, and customers to deeply understand corner cases — especially for the Indian accent, which is the most challenging due to its vast regional variation and phonetic complexity. This close collaboration, combined with relentless efforts from the world-class research and engineering teams at Krisp, has culminated in another major step forward now.

Today, we’re launching Accent Conversion v3.7, delivering significant improvements in naturalness and voice stability. This release is currently focused on the Indian accent pack, with support for other accents rolling out soon.

The following sections summarize the key improvements, benchmarking methodology, and a side-by-side comparison of Accent Conversion v3.7 with v3.5.

Key Improvements in AC v3.7

1. Naturalness: The converted speech sounds even more human-like and natural, with much improved filler-sound handling. Here, expert-rated naturalness scores improved by +14%. Crowdsourced evaluations confirm it with a +6% gain.
2. Voice Stability: Enhanced consistency in pitch and tone throughout the utterance, helping avoid unnatural fluctuations, especially for thick accents. This contributed to improved naturalness and clarity scores across all metrics.
3. Speech & Audio Clarity: Improvements were noted in both intelligibility and the reduction of artifacts and distortions. Speech Clarity scores rose by 5% in expert assessments, with corresponding enhancements across Meta metrics.
4. Pronunciation Accuracy: There’s a gain in objective metrics as well, about a 4% relative improvement in Phoneme Error Rate (PER), which can be attributed to more conversational data inclusion in the training. Here, some noticeable accent-specific enhancements in phoneme pronunciation, such as more native-like articulation of “R” and “L”, contribute to a +5% increase in the Accent Conversion score.

Evaluation Results

For subjective and objective evaluations, 78 real-world recordings were sampled.

For the crowdsourced evaluation, each recording received exactly 30 independent votes to ensure statistical confidence, 2340 total votes.

The results shown in the table below represent aggregated averages across all recordings.

Metric	IN AC v3.5	IN AC v3.7	Comment
Expert Evaluation – Natural speech (1 to 5)	3.7	4.2 (+14%)	Speech sounds even more human-like, with much improved filler-sound handling
Expert Evaluation – Speech Clarity (1 to 5)	4.0	4.2 (+5%)	Speech is with fewer artifacts and clearer, especially in slurred and mumbling segments
Expert Evaluation – Accent Conversion (1 to 5)	4.3	4.5 (+5%)	Accent-specific enhancements in phoneme pronunciation, such as more native-like articulation of “R” and “L”
Crowdsourced Evaluation – “How natural does the voice sound?” (1 to 5)	3.4	3.6 (+6%)	78 real-world audio recordings assessed by 30 participants
Crowdsourced Models’ Comparison – Which option sounds more natural?	1242	1878 (+20%)	78 real-world audio recording pairs were evaluated, with each pair assessed by 40 participants
Meta Aesthetic – Natural speech (1 to 10)	5.6	5.8 (+4%)
Meta Aesthetic – Speech Clarity (1 to 10)	7.5	7.6 (+1%)

Comparative audio samples

Listening Tip: For the most accurate and immersive comparison between v3.5 and v3.7 Accent Conversion, we recommend using quality headphones.

This helps highlight the improvements in clarity, naturalness, and speaker identity preservation that may be less perceptible on laptop or mobile speakers.

Appendix

Subjective Evaluation

Our evaluation was conducted across two structured tracks: expert panel ratings and crowdsourced listener preferences, designed to capture both technical precision and human perception.

Real-world agent calls have been sampled to represent a diverse set of speakers and input conditions, including, but not limited to

• Accent level – high, medium, low
• Speech rates and fluency
• Background conditions (quiet, noisy, multi-speaker environments)

Evaluators scored each recording across four qualitative dimensions using a 5-point Likert scale:

1. Expert Panel Evaluation

Six expert evaluators independently rated matching audio pairs — each pair consisting of the same original voice converted by AC v3.5 and AC v3.7.

To eliminate bias:

• File names were anonymized (no version markers)
• The order of samples was randomized
• Scoring was blind and individual (no group discussion)

2. Crowdsourced Evaluation

To further simulate real-world user perception, a blind A/B test was run with a pairs of recordings: AC v3.5 vs. AC v3.7.
78 real-world audio recording pairs were evaluated, with each pair assessed by 40 participants, resulting in 3,120 votes overall.

Participants were asked the following question:
“Which option sounds more natural (i.e., more human-like)?”

Results:

• Version 3.5 was selected 1242 times
• Version 3.7 was selected 1878 times

Evaluation metrics

Accent Conversion performance was measured across four key dimensions. These were selected based on real-world call center priorities such as clarity, naturalness, and robustness.

Objective Evaluation

For objective evaluation, the same set of recordings was processed using the Meta Audiobox Aesthetics and captured metrics strongly correlated to Natural Speech and Speech Clarity. Additionally, to quantify how each system impacts phoneme accuracy, all recordings were also processed using the Facebook NN Phonemizer, which is strongly correlated with the Accent Conversion metric.

•  these metrics are derived from waveform-level analysis and do not require transcript or linguistic alignment, making them ideal for evaluating accent conversion outputs that vary in delivery and prosody.

The post Introducing Krisp Accent Conversion v3.7 appeared first on Krisp.

Note: The Turn-Taking model is included in the VIVA SDK offering at no additional charge.

What is turn-taking?

Turn-taking is the fundamental mechanism by which participants in a conversation coordinate who speaks when. While seemingly effortless in human interaction, in human to AI agent conversations modeling this process computationally is highly complex. In the context of Voice AI Agents (including voice assistants, customer support bots, and AI meeting agents), turn-taking decides when the agent should speak, listen, or remain silent.

Without effective turn-taking, even the most advanced dialogue systems can come across as unnatural, unresponsive, and frustrating to use. A precise and lightweight turn-taking model enables natural, seamless conversations by minimizing interruptions and awkward pauses while adapting in real time to human cues such as hesitations, prosody, and pauses.

In general, turn-taking includes the following tasks:

• End-of-turn prediction – predicting when the current speaker is likely to finish their turn
• Backchannel prediction – detecting moments where a listener may provide short verbal acknowledgments like “uh-huh”, “yeah”, etc. to show engagement, without intending to take over the speaking turn.

In this article, we present our first audio-based turn-taking model, which focuses on the end-of-turn prediction task using only audio input. We chose to release the audio-based turn-taking model first, as it enables faster response times and a lightweight solution compared to text-based models, which usually require large architectures and depend on the availability of a streamable ASR providing real-time, accurate transcriptions.

Approaches to Turn-Taking

Solutions to Turn Taking problem are usually implemented in AI models, which use audio and/or text representation.

1. Audio-based

Audio-based approaches rely on analyzing acoustic and prosodic features of speech. These features include, changes in pitch, energy levels, intonation, pauses and speaking rate. By detecting silence or overlapping speech, the system predicts when the user has finished speaking and when it is safe to respond. For example, a sudden drop in energy followed by a pause can be interpreted as a turn-ending cue. Such models are effective in real-time, low-latency scenarios where immediate response timing is critical.

2. Text-based

Text-based solutions analyze the transcribed content of speech rather than the raw audio. These models detect linguistic cues that indicate turn completion, such as sentence boundaries, punctuation, discourse markers (e.g., “so,” “anyway”), natural language patterns or semantics (e.g., user might directly ask the bot not to speak). Text-based systems are often integrated with dialogue state tracking and natural language processing (NLP) modules, making them effective for scenarios where accurate semantic interpretation of user intent is essential. However, they may require larger neural network architectures to effectively analyze the linguistic content.

3. Audio-Text Multimodal (Fusion)

Multimodal solutions combine both acoustic and textual inputs, leveraging the strengths of each. While audio-based methods capture real-time prosodic cues, text-based analysis provides deeper semantic understanding. By integrating both modalities, fusion models can make accurate and context-aware predictions of turn boundaries. These systems are effective in complex, multi-turn conversations where relying on either audio or text alone might lead to errors in timing or intent detection.

Challenges of turn-taking

Hesitation and filler words

In natural dialogue, speakers often take a pause using fillers like “um” or “you know” without intending to give up their turn. For instance:

“I think we should, um, maybe –” [The agent jumps in, assuming the sentence is over]

Here, a turn-taking system must distinguish hesitation from completion, or risk interrupting too early.

Natural pauses vs. true end-of-turns

Pauses are not always indicators that a speaker has finished. For example:

“Yesterday I woke up early, then… [pause] I went to work…”

A model might misinterpret the pause as a turn boundary, generating a premature response and breaking the conversational flow.

Quick turn prediction

Minimizing response latency is essential for maintaining natural conversational flow. Humans tend to respond quickly, sometimes even reactively, when the end of the speech is obvious. If a model fails to predict the turn boundary fast enough, the system may sound sluggish or unnatural. The challenge is to trigger responses at just the right moment – early enough to sound fluid, but not so early that it risks interrupting the speaker.

Varying speaking styles and accents

People speak in diverse rhythms, intonations, and speeds. A fast speaker with sharp pitch drops might appear to end a sentence even when they haven’t. Conversely, a slow, melodic speaker may stretch syllables in ways that confuse timing-based systems. Modeling these variations effectively requires a neural network–based approach.

Krisp’s audio-based Turn-Taking model

Recently Krisp had released AI models for effective noise cancellation and voice isolation for Voice AI Agent use-cases, particularly improving pre-mature turn taking caused by background noise. See more details. This technology is widely deployed and has recently passed a 1B mins/month milestone.

It was only natural for us to take on a larger problem of turn-taking (TT). In this first iteration, we designed a lightweight, low-latency, audio-based turn-taking model optimized to run efficiently on a CPU. The Krisp TT model is built into  Krisp’s VIVA SDK, where using the Python SDK you can easily chain it with the Voice Isolation models , placing it in front of a voice agents to create a complete, end‑to‑end conversational flow, as shown in the following diagram.

Here, the TT model continuously outputs a confidence score (probability) ranging from 0 to 1, indicating the likelihood of a shift – a point where a speaker is expected to finish their turn. It operates on 100ms audio frames, assigning a shift confidence score to each frame. To convert this score into a binary decision, we apply a configurable threshold. If the score exceeds this threshold (Δ), we interpret it as a shift (end of turn) prediction; otherwise, the model considers the current speaker is still holding the turn.

We also define a maximum hold duration, which defaults to 5 seconds. The model is designed such that, during uninterrupted silence, the confidence score gradually increases and reaches a value of 1 precisely at the end of this maximum hold period.

Comparison with other Turn-Taking models

Let’s take a closer look at how other solutions handle the turn-taking problem in comparison to Krisp.

Simple VAD (Voice Activity Detection)

The basic VAD-based approach is as straightforward as it gets – if you taken a pause in your speech, you have probably have finished your turn. Technically, once a few seconds of (usually configurable) silence is detected, the system assumes the speaker has finished and hands over the turn. While efficient, this method lacks awareness of conversational context and often struggles with natural pauses or hesitant speech. In our comparisons, we use the Silero-VAD model with a 1-second silence detection window as a simple VAD-based turn-taking approach.

SmartTurn

SmartTurn v1 and SmartTurn v2 by Pipecat are open-source AI models, designed to detect exactly when a speaker has finished their turn. We picked them for in-depth comparison because like Krisp TT, they are audio-based models.

Interestingly, SmartTurn models introduce a hybrid strategy. They first wait for 200ms of silence detected by Silero VAD, then evaluate whether a turn shift should occur. If the confidence is too low to switch, the system defers the decision. However, if silence persists for 3 seconds (default value, configurable parameter in SmartTurn), it forcefully initiates the turn transition. This layered approach aims to strike a balance between speed and caution in handling user pauses.

Tested Models

The following table gives a high-level comparison between the contenders

Test Dataset

The test dataset was built using real conversational recordings, with manually labeled turn-taking (shift) and hold scenarios (hold). A turn-taking instance marks a point where one speaker hands over the conversation, we will call a shift, while a hold scenario captures cases where the speaker continues after a brief pause, filler words, or unfinished context.

The dataset consists of 1,875 labeled audio samples, including a significant number of labeled shift and hold scenarios. Each audio file is annotated to include the silence at the end of a speaker’s segment – either resulting in a turn shift or a hold. The test data was annotated according to multiple criteria, including context, intonation, filler words (e.g., “um,” “am”), keywords (e.g., “but,” “and”), and breathing patterns.

Below are the statistics on silence duration for each scenario type as well as the distribution of shift and hold cases based on mentioned criteria.

Training Dataset

Our training dataset comprises approximately 2,000 hours of conversational speech, containing around 700,000 speaker turns.

Evaluation: Prediction Quality Metrics

To assess the performance of the turn-taking model, we used a combination of classification metrics and timing-based analysis:

AUC: The AUC is the area under the ROC curve. A higher AUC value indicates better classification performance, here ROC (receiver operating characteristic) shows the trade-off between the true positive rate and the false positive rate as the decision threshold is varied, for more details on AUC and other metrics read here.

Evaluation: Latency vs. Accuracy tradeoff (MST vs FPR)

We realized that there is a natural tradeoff between the accuracy and latency, i.e. how quickly the system detects a true shift. We can reduce the latency by lowering the threshold, however, it will likely lead to increased false-positive rate (FPR) and unwanted interruptions. On the other hand, we don’t want to wait too long to predict a shift, because the increased latency will result in awkward interaction (see the chart below).

Therefore, the latency to accuracy relationship is important and here we measure TT system’s latency by mean shift time (MST). The shift time is defined as the duration between the onset of silence and the moment of predicting end-of-turn (shift). If the model outputs a confidence score, the end-of-turn prediction can be controlled via a threshold. This makes the threshold an important control lever in the trade-off between reaction speed and prediction accuracy:

• Higher thresholds result in delayed shift predictions, which help reduce false positives (i.e., shift detections during the current speaker hold period which leads to interruption from the bot). However, this increases the mean shift time, making the system slower to respond.
• Lower thresholds lead to faster responses, decreasing mean shift time, but at the cost of increased false positives, potentially causing the bot to interrupt speakers prematurely.

To visualize this trade-off, we plot a chart showing the relationship between mean shift time calculated in end-of-speech cases and false positive (interruption) rate as the threshold varies from 0 to 1. To provide a comparative summary of models, we plot these charts. A lower curve indicates a faster mean response time for the same interruption rate – or, from another perspective, fewer interruptions for the same mean response time. Here you can see the corresponding plots for Krisp TT, SmartTurn v1 and SmartTurn v2. Note that we can’t directly visualize such a chart for the VAD-based TT, as MST vs FPR requires a model that outputs a confidence score, whereas the VAD-based model produces binary outputs (0 or 1). The same limitation applies to AUC-shift computation shown in the table above.

This basically means that the Krisp TT model has considerably faster average response time (0.9 vs. 1.3 seconds at a 0.06 FPR) compared to SmartTurn to produce a true-positive answer.

To summarize the overall latency-accuracy tradeoff, we also compute the area under the MST vs FPR curve. This single scalar score captures the model’s ability to respond quickly while minimizing interruptions across different thresholds. A lower area indicates better performance.

Evaluation Results

It’s important to note that the Krisp TT model delivers comparable quality in terms of predictive quality metrics and significantly better quality in terms of latency vs accuracy tradeoff while being 5-10x smaller and optimized to run efficiently on a CPU. The VAD-based turn-taking approach is more lightweight, but it performs significantly worse than dedicated TT models – highlighting the importance of modeling the complex relationships between speech structure, acoustic features, and turn-taking behavior.

Demo

Here’s a simple dialogue showing how Krisp’s Turn-Taking model works in practice. In the demo, you’ll hear intentional utterances, pauses, filler words and interruptions. The response time you observe includes the Turn-Taking model’s speed, plus the latency from the speech-to-text (STT) system and the language model (LLM).

Krisp’s Turn-Taking Model

Krisp’s TT model vs Pipecat’s SmartTurn V2

This demo compares Krisp’s Turn-Taking model with Pipecat’s SmartTurn model (3-second default value, configurable parameter in SmartTurn). To highlight the differences visually, we’ve also overlaid a speech-to-text transcript on the video.

Future Plans

Improved Accuracy in TT

While this initial, audio-based TT model provides balanced accuracy and latency, it is mainly limited to analyzing prosodic and acoustic features, such as changes in intonation, pitch and rhythm. By analyzing linguistic features like the syntactic completion of a sentence we can further improve the accuracy of the TT model.

We plan to build the following features as well:

• Text-based Turn-Taking: This model will use text only input and predict end-of-turn with a custom Neural Network trained for this use case.
• Audio-Text Multimodal (Fusion): This model will use both audio and text inputs to leverage the best from these two modalities and give the highest accuracy end-of-turn prediction.

Early prototypes show promising results, with the multimodal approach outperforming the audio-based turn-taking models noticeably.

Backchannel support

Backchannel detection is another challenge encountered during the development of Voice AI agents. The “backchannel” is the secondary or parallel forms of communication that occur alongside a primary conversation or presentation. It encompasses the responses a listener gives to a speaker to indicate they are paying attention, without taking over the main speaking role.

While interacting with AI agent, in some cases, the user may genuinely want to interrupt – to ask a question or shift the conversation. In others, they might simply be using backchannel cues like “right” or “okay” to signal that they’re actively listening. The core challenge lies distinguishing meaningful interruptions from casual acknowledgments.

Our roadmap includes the release of a reliable dedicated backchannel prediction model.

The post Audio-only, 6M weights Turn-Taking model for Voice AI Agents appeared first on Krisp.

Recently, Sanas filed a lawsuit against Krisp. While we prefer to compete in the marketplace, we will not let this attempt to distort the facts and assail our reputation go unanswered.

Let’s set the record straight.

1. The 2022 Sanas meetings went nowhere — and for good reason.

Krisp met with Sanas under NDA in 2022, but those discussions were brief and unproductive. Sanas demonstrated an early version of its product, which lacked maturity and failed to meet our expectations. The company was vague, unresponsive to basic technical questions, and did not share any information that could remotely be considered a trade secret. Ultimately, there was no trust or alignment — and no basis for collaboration.

2. We walked away, citing product limitations and a lack of alignment.

Based on Sanas’s demonstration of the technology our conclusion was that Sanas’ technology had very limited technical capabilities and obvious drawbacks. We made a clear decision not to move forward with Sanas. Our reasons were straightforward: we saw limited technology performance and integration visibility, and misalignment in business communication from Sanas.

These factors made clear that a partnership with Sanas would not meet Krisp’s standards or goals.

3. We built something fundamentally better.

Accent conversion has always been part of Krisp’s technology roadmap. With no viable market alternative, Krisp’s world-class Voice AI team drew on its pioneering work in noise cancellation, background-voice isolation, emotion conversion, and other proprietary technologies to create a best-in-class accent conversion technology.

We place a strong focus on solving the accent conversion problem offline with high fidelity and close retention of the original voice of the speaker. Once this version of the problem is settled, a new architecture, specifically designed for low-CPU footprint and real-time application, performs accent conversion, based, among other things, on the solution of the offline problem.  A key component in the design of this architecture is the ability of retaining acoustic details of the input, allowing smooth and natural flow of the converted voice. Our design does not rely on specialized alignment modules, which are key components in Sanas’s patents. This critical difference is the key reason Krisp outperforms Sanas.

We didn’t use Sanas’ technology — we far surpassed it.  And now, as part of its lawsuit, Sanas is trying to claim rights to Krisp’s technology, which Krisp independently developed and secured at great cost and effort.  While Sanas would certainly benefit from copying Krisp’s technology, its efforts to forcibly take Krisp’s patent rights are completely baseless.

Moving forward.

The lawsuit has no impact on our operations, product roadmap, or customer commitments. It’s business as usual at Krisp. We will vigorously defend our innovations and set the record straight through the legal process.

Thank you for your continued trust in Krisp. We’ll continue to share updates here as the case develops.

The post Krisp Statement on Sanas Lawsuit appeared first on Krisp.

BERKELEY, CA, July 16, 2025 — Krisp, the leader in real-time Voice AI technology, today announced the launch of VIVA, its voice isolation AI model and software development kit (SDK) built for Voice AI agents, while achieving 1 billion minutes of monthly Voice AI processing across global deployments. The milestone reinforces Krisp’s position in the industry as a leader in real-time voice isolation and noise cancellation, powering the most advanced voice AI products in the market. It also reflects a growing demand for real-time, low-latency voice infrastructure as voice becomes the dominant mode of human-AI interaction.

VIVA delivers server-side voice isolation by seamlessly integrating into an application’s audio path. It empowers voice AI agents by improving turn-taking, enhancing voice activity detection, and preventing false interruptions, leading to more natural and effective conversations.

Already integrated into Daily, Vodex.ai, Vapi, Ultravox.ai (formerly Fixie.ai), LiveKit, and the world’s largest AI labs, VIVA is driving measurable impact:

• Improving turn-taking accuracy by 3.5x
• Enabling smoother interactions by resulting in 50% fewer dropped calls
• Delivering a strong customer experience with 30% higher customer satisfaction scores (CSAT) 

“When our development team demonstrated Krisp’s capabilities, we were blown away. Seeing our bot continue uninterrupted, even amidst loud office noise, was a game-changer for us,” said Kumar Saurav, CTO of Vodex. “It felt like a whole new level of innovation.”

“Reaching this volume of processed audio is a reflection of how broadly integrated Krisp’s Voice AI technology has become,” said Davit Baghdasaryan, CEO and Co-Founder of Krisp. “As voice agents take center stage, clarity is non-negotiable. VIVA delivers the voice isolation backbone these systems need to operate reliably and conversationally in the real world.”

Built for high-throughput, low-latency environments, VIVA processes billions of audio requests each month, enabling developers to build more responsive and natural AI agents, from customer support to virtual companions.

To learn more about VIVA, visit https://krisp.ai/developers/#technologies

The post Krisp Launches VIVA SDK and Surpasses 1B Minutes of Voice AI Processing per Month Milestone appeared first on Krisp.

It’s built for modern professionals who need to stay organized and follow up fast, wherever work happens.

Please note: At this time, the Krisp Mobile App does not support noise cancellation due to current platform limitations. This feature remains available on the desktop version.

What You Can Do with Krisp Mobile?

• Record and transcribe in-person meetings with a single tap
• Upload voice notes or audio files for instant transcription
• View and manage your entire meeting history on mobile
• Send the Krisp AI bot to Zoom, Google Meet, or Microsoft Teams calls
• Review summaries, action items, and shared content from anywhere

Why Krisp Mobile Fits Modern Workflows?

Modern professionals don’t just work from one desk or one location. Krisp Mobile gives you continuity, clarity, and control across every meeting touchpoint.

• Capture insights from in-person meetings that would otherwise be lost
• Stay on top of your meeting backlog without needing your laptop
• Follow up faster with AI-generated notes and summaries
• Make meetings searchable, sharable, and structured – on the go

Who Is the Krisp Mobile App For?

The Krisp Mobile App is available for:

• iPhone (via the App Store)
• Android (via the Google Play Store)

It’s free to download and integrates with your existing Krisp account. Whether you’re a solo founder, part of a remote team, or leading hybrid meetings, the mobile app extends Krisp’s powerful meeting assistant to wherever you are.

Download the app and start capturing smarter conversations today — whether you’re meeting in person or online.

The post Introducing the Krisp Mobile App: Smarter Meetings, Anywhere You Go appeared first on Krisp.

Ready to try it? Install the Krisp Chrome Extension from the Chrome Web Store now!

Seamlessly Capture Every Meeting

With the Krisp Chrome extension, you can now record, transcribe, and summarize your meetings directly from your browser. No need to worry about taking notes or manually capturing key points – Krisp does it all for you. If you’re using Google Meet, Krisp detects your meeting and offers an easy way to enable AI-powered assistance.

Smart Transcription and Summaries

Say goodbye to scrambling for Meeting Notes. Krisp automatically generates real-time transcripts, highlights key topics, and produces concise AI-powered summaries – so you can focus on the conversation while Krisp takes care of the details.

Deeper Integration with Google Meet, Calendar, and Agenda

If you’re already using the Krisp desktop app, adding the Chrome extension unlocks even better and deeper integration with Google Meet, Calendar, and Agenda. This means smarter meeting detection, seamless transcription directly in your browser, and enhanced scheduling capabilities. You can even add discussion points to upcoming meetings directly from your Calendar and view past meeting topics in one place, making it easier to stay organized and prepared.

Stay Present, Stay Productive

Instead of multitasking during meetings, let Krisp handle the note-taking. With clear, structured transcripts and automated summaries, you’ll always have an easy way to revisit key points and share insights with your team.

Try Krisp for Chrome today and experience effortless meeting transcription, recording, and summarization – all in one tool.

The post Krisp for Chrome: AI-Powered Meeting Transcription, Recording, and Summarization appeared first on Krisp.