Revenue teams

Sales call analysis with words and tone

Review recorded sales calls with a transcript and labels for emotion and speaking style. Find changes in delivery, replay the relevant passages, and consider them alongside CRM notes.

For teams building this workflow into their own product. Start with prerecorded English audio; Oruk returns structured analysis through the API.

Try your audio Build with the API Estimate cost

No account needed to try the public demo.

Illustrative output

A transcript with labels for vocal delivery

This actually sounds like exactly what we have been trying to solve — how soon could we start?

excited 0.82hopeful 0.7energetic 0.55

Example labels for this interface concept. Analyze your recording to inspect actual model output.

Unified analysis request

curl https://speech-api.oruk.ai/v1/audio/analysis \
  -H "Authorization: Bearer $ORUK_API_KEY" \
  -H "X-Request-ID: $(uuidgen)" \
  -F "model=oruk-resonance" \
  -F "file=@recording.wav"

Example implementation

Where Oruk fits in your workflow

Your input: A completed English sales recording associated with a call record in your CRM.
Oruk returns: A timed transcript with vocal-expression labels that can be inspected alongside the conversation.
Your application: Attach replayable passages to the CRM record. A coach reviews the audio and adds a contextual note for the next conversation.

Evaluate the result in your pilot

Measure time to locate a coachable passage and reviewer agreement on relevance. Test whether notes become more specific; do not use acoustic scores as a prediction of intent or likelihood to buy.

How it works

Send the recording

Upload a prerecorded sales call for post-call review.

Review words and delivery

Read the transcript alongside emotion and speaking-style scores for each segment.

Review and coach

Feed the labels into call scoring and coaching workflows alongside CRM context and reviewer judgment.

What you can build

Find passages worth reviewing for questions and objections
Replay changes in delivery alongside the transcript
Coach with specific moments from a recorded call
Add vocal-expression scores to call transcripts

Deployment safeguards

Treat emotion labels as acoustic measurements, not a verdict on intent
Validate on your call recording conditions, languages, and accents
Keep multiple labels and uncertainty rather than one definitive state
Disclose recording and analysis according to applicable consent rules

Responsible-use guidance

Related resources

AI call analytics Contact center analytics Voice call sentiment analysis Voice of customer analytics Meeting speech understanding Qualitative research speech analysis Speech analytics API Speech emotion recognition API API capabilities and scope API documentation Build a speaker-turn review workflow Stream transcription and phrase emotion Pricing