Modulate Adds Twilio Ventures Backing and Faster AI Voice Detection

Modulate has announced new investments from Twilio Ventures and Kayak co-founder Paul English as it expands the technology businesses can use to identify synthetic callers and supervise AI voice agents. The company says its latest models can identify an AI-generated voice in a median of 1.6 seconds, down from 2.25 seconds, while maintaining detection accuracy above 99.1% on its real-world AI and human call evaluation.

The investment follows Modulate’s $25 million financing announced in September, led by Future Ventures with participation from Hyperplane and Lakestar. The company has not disclosed the size of the additional investments. Alongside the financing, it is adding more than a dozen audio-native signals to its Velma platform to help enterprises understand both who—or what—is calling and how an AI-led conversation is unfolding.

The distinction is becoming central to voice automation. A synthetic caller might be a useful assistant making an appointment, or a cloned voice attempting impersonation. Detecting generated speech provides one piece of evidence; deciding what to do with the call requires a broader view of its behavior and context.

Faster Detection While a Call Is Still Underway

Modulate says the reduction in median detection time lets businesses identify synthetic speech early enough to route a call, flag it for review, or apply additional verification while the conversation continues. Its system examines the underlying audio without depending on watermarks inserted by individual voice-generation providers, including for newer speech-to-speech and full-duplex models.

The change from 2.25 to 1.6 seconds represents about a 29% reduction in the company’s reported median. It is a detection-time measure, rather than a guarantee that every call will be classified in that interval or that a complete security workflow will finish that quickly. The announcement does not provide the evaluation sample size or a breakdown of false positives and false negatives behind the greater-than-99.1% accuracy figure.

“Call operators – human or AI agent – must be able to recognize what’s happening in those conversations and respond appropriately while the interaction is still ongoing,” said Carter Huffman, CEO and co-founder of Modulate.

For contact centers, the operational benefit is the opportunity to intervene before a conversation has finished. A warning delivered after an account change or sensitive disclosure has already occurred serves a different purpose from a signal available during the interaction.

How Velma Combines Specialized Audio Models

Velma uses what Modulate calls an Ensemble Listening Model, or ELM: an architecture that coordinates specialized models rather than relying entirely on a single general-purpose model to interpret a transcript. The company says its system brings together more than 100 models covering signals such as emotion, tone, intent, cadence, synthetic speech, and conversational behavior.

Its product description explains that an orchestration layer combines lower-level signals into higher-level assessments while preserving links to the underlying evidence. Time-stamped events can indicate where a conversation changed, giving an operations team something more specific to review than an unexplained call-level risk score.

A transcript captures words, but it does not preserve every pause, interruption, change in emphasis, or delivery pattern. Modulate’s approach adds acoustic information to the analysis so developers can examine how a conversation proceeds alongside what participants say.

The company’s deepfake-detection documentation illustrates that distinction at the API level. It describes acoustic classification of audio segments, with time boundaries, verdicts, and confidence scores, and supports both recorded files and live streams. A detection confidence score is evidence for a classification, rather than proof of a caller’s identity or intentions.

Synthetic Speech Is Not the Same as Fraud

Modulate explicitly separates these questions in its voice-fraud screening guide: deepfake detection evaluates whether a voice is synthetic, while conversation analysis evaluates behavior. A legitimate AI assistant can use generated speech; a human caller can attempt social engineering without any voice synthesis.

That distinction also matters for people using assistive speech technology. A synthetic-voice flag alone is an insufficient reason to treat a caller as malicious. In the new release, Modulate says Velma can combine that flag with signals associated with intent, manipulation, tone, and conversational behavior to support more informed handling.

The practical goal is a graduated response: ordinary routing for permitted automation, additional verification where a transaction warrants it, and escalation when the conversation presents suspicious behavior. The detection system supplies evidence; the organization’s policies determine the response.

Monitoring the Quality of AI Voice Agents

The new Velma signals also target a less dramatic but commercially important problem: an AI agent can sound fluent while delivering a poor service experience. Modulate says the additions help evaluate response timing, audio quality, and conversational misunderstandings that transcript-only analytics can miss.

On its AI guardrails page, the company describes Velma as monitoring participants rather than acting as the conversational agent itself. Customers can configure monitoring around operating procedures and expected behavior, then send signals into existing systems through APIs and webhooks.

This separates the system doing the talking from the system assessing the interaction. It gives teams a way to investigate where an agent is causing frustration, going outside policy, or failing to respond appropriately, and use those findings to improve deployment.

Twilio Backing Builds on an Existing Connection

Twilio Ventures focuses on AI, developer tools, and customer-engagement businesses, making audio intelligence relevant to its investment remit. Modulate already has a technical connection to Twilio: a May 2025 announcement described compatibility for its VoiceVault and ToxMod products, including Twilio Media Streams-compatible APIs for bringing live call audio into its systems.

The new investment builds on that history, although the announcement does not establish a new exclusive distribution agreement. Modulate says the capital will support research, product development, developer adoption, partnerships, and broader deployment options.

September’s funding announcement placed the same priorities at the center of its expansion beyond earlier voice-safety applications. With this update, the company is bringing detection and supervision closer together: helping enterprises recognize generated speech, examine the surrounding behavior, and assess whether their own voice agents are doing the job intended.