Signed in as:
filler@godaddy.com
Signed in as:
filler@godaddy.com

Every sentence, for every speaker, on every earnings call, for the R3K transcribed. Repetitions, filler words, hedging words and other aspects of word cadence are tracked and scored. SCA transcribes the earnings calls itself - we want all that linguistic messiness that are scrubbed from commercial transcripts.

Using a speaker specific baseline, the audio for each sentence is analyzed at the 22 (µs) micro -second level. Features such as speech rate, vocal tremors, energy and imbalance are generated. Vocal scores are generated which map to the speaker's emotional state.

Empirical support for vocal scores over various holding periods. Across the Russell 3000, these signals show statistically significant relationships with subsequent stock returns, even after controlling for text sentiment and traditional financial variables. The results confirm that vocal leakage during high-stakes communication, especia
Empirical support for vocal scores over various holding periods. Across the Russell 3000, these signals show statistically significant relationships with subsequent stock returns, even after controlling for text sentiment and traditional financial variables. The results confirm that vocal leakage during high-stakes communication, especially in Q&A is a meaningful investable source of information.

M&A calls occur at moments of high strategic and financial consequence, often immediately after deal announcements when executives have had little time to rehearse. These calls reveal management’s true conviction about valuation, synergies, integration risk, and competitive positioning. Because the stakes are high and the messaging is le
M&A calls occur at moments of high strategic and financial consequence, often immediately after deal announcements when executives have had little time to rehearse. These calls reveal management’s true conviction about valuation, synergies, integration risk, and competitive positioning. Because the stakes are high and the messaging is less polished than on earnings calls, vocal and linguistic leakage is more likely—and more informative.

SCA captures sentence-level vocal stress markers, confidence cues, energy patterns, and deviations from each executive’s established baseline. Linguistic models analyze uncertainty language, defensiveness, deal-justification framing, and Q&A posture. The dataset links these features to deal-topic segments such as synergies, financing, and integration.

SCA is the only platform that systematically extracts voice-based conviction signals from M&A calls across the entire public-company universe. By anchoring every executive to their personal behavioral baseline, SCA identifies when deal explanations diverge from typical communication patterns. This enables investors to isolate which parts
SCA is the only platform that systematically extracts voice-based conviction signals from M&A calls across the entire public-company universe. By anchoring every executive to their personal behavioral baseline, SCA identifies when deal explanations diverge from typical communication patterns. This enables investors to isolate which parts of a merger narrative exhibit stress or confidence, creating a new source of differentiated insight for traditional, systematic, merger-arb and event-driven strategies.

Each sentence is transcribed and coupled with 19 proprietary voice features generated for every speaker and every sentence on every FOMC press conference since April 2011.

14 proprietary linguistic features generated for every speaker and every sentence on every FOMC press conference since April 2011.

For each speaker on the press conference, the average Voice and Linguistic Feature - useful for creating baselines
Copyright © 2025 Speech Craft Analytics Inc. - All Rights Reserved.