- SENTIMENT
- TOPICS
- TRANSCRIPTS
- HUMAN
Short answer
How can I extract sentiment and topics from interviews?
You submit your audio recordings to Rev.ai, and your AI client pulls the sentiment scores and key topics from the transcripts. This gives you a structured view of participant feelings and recurring themes.
The research outcomes.
What your data becomes.
The AI turns raw audio into organized research insights.
SENTIMENT
Emotional scoring
The AI identifies the tone of the conversation. You get specific scores that show if a participant was frustrated, happy, or neutral.
TOPICS
Key theme extraction
The agent pulls out the recurring subjects discussed. This helps you see which features or pain points come up most often.
TRANSCRIPTS
Textual records
Every recording is converted into text. You can then ask your AI to search for specific quotes or phrases within those transcripts.
HUMAN
Manual verification
You still need to review the results. The AI provides the data, but you decide which insights are actually meaningful for your research.
The workflow
What your AI does when the audio arrives.
The process moves from raw audio to structured insights.
Upload audio
Your AI sends the audio file to the transcription service to start the processing job.
submit_stt_jobMonitor progress
The agent checks the status of the transcription to ensure the file is ready for analysis.
get_stt_jobExtract sentiment
Once the text is ready, the AI pulls the emotional scores from the recording.
get_sentiment_analysis_resultIdentify themes
The agent finishes by pulling the specific topics that were discussed during the session.
get_topic_extraction_result
Try it
Copy these to start.
Use these prompts to trigger the analysis.
Starting points
These are opening lines. Swap out the file names or project names with your actual data.
Rev.ai Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_8mAs5Sblbrb5mUGJJRfEyGyrwQy1HbvowtnIJANN/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Rev.ai capabilities are ready to use.
{
"mcpServers": {
"revai-mcp": {
"url": "https://edge.vinkius.com/vk_preview_8mAs5Sblbrb5mUGJJRfEyGyrwQy1HbvowtnIJANN/mcp"
}
}
}Analyze the sentiment for the interview file 'user_study_01.mp3'.
What were the main topics discussed in the 'customer_feedback_session.wav' recording?
Give me a summary of the emotional scores from the 'product_testing_v2' audio.
Extract the key themes from the 'stakeholder_interview.mp3' file.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Rev.ai once, then ask.
Just link your account once. Your credentials stay encrypted, and you can immediately start asking your AI to process your audio files.
Connect Rev.ai to your AIFAQ
How the analysis behaves
- 01
Can the AI edit my audio files?
No. The AI only reads the data from the files to extract text and sentiment.
- 02
Does the AI automatically delete my recordings?
No. The AI has no capability to delete or modify your files in Rev.ai.
- 03
Can I ask questions about the transcript after it's done?
Yes. Once the transcription is complete, you can use your AI client to ask anything about the text.
- 04
How does the AI know what the topics are?
The AI uses a specific tool to scan the completed transcript for recurring themes and subjects.
- 05
Can the AI perform the transcription itself?
No. The AI uses Rev.ai to handle the actual speech-to-text conversion.
More questions about Rev.ai? The Connector page answers them. See everything the Rev.ai Connector can do
Connect Rev.ai to Claude, Cursor, ChatGPT & more
