From IonBin New tools and workflows every week. See what’s new
Find themes across customer interviews
Research & market intelligence · Marketing content & social · checked 2026-10-17
Pull interview transcripts from Wave or Otter over MCP, have your AI assistant collect quotes into a CSV, analyze themes and counts in Julius AI, and write the findings yourself.
Independent review. IonBin has no partnership with any tool on this page and was not paid for this page. Our evaluation is our own, based on public documentation and our research. Product names are trademarks of their owners and are used for identification only. How disclosure works.
Goal
Pull patterns out of a dozen interviews in an afternoon.
Check themes against the transcripts and write the findings
Human step
Confirmed
Confirmed means the vendor documents it (linked). It doesn't mean IonBin has tested it. AI-platform and human steps need no source.
Human approval
You validate themes against the raw transcripts.
Watch out for
Keep the human approval step: You validate themes against the raw transcripts.
Starter prompt
Goal: Pull patterns out of a dozen interviews in an afternoon. Tools involved: Wave, Otter, Julius AI. Your part: supplies transcripts through get_transcript on its mcp server; supplies transcripts through the fetch tool on its mcp server; collects quotes into a csv with interview, speaker and draft theme columns. Work step by step, show me each draft or proposed change, and wait for my approval before anything is sent, published, signed, filed or changed in a live system.
Assembled from this page’s goal and steps. Paste it into your AI platform and adjust it to your situation.
Wave: pairing not named in vendor docs; Otter: pairing not named in vendor docs
ChatGPT
To verify
Otter: pairing not named in vendor docs
Gemini
To verify
Wave: pairing not named in vendor docs; Otter: pairing not named in vendor docs
Perplexity
To verify
Wave: pairing not named in vendor docs; Otter: pairing not named in vendor docs
Computed from the MCP and API steps only: "Confirmed" needs the tool's docs to name the platform and the platform to support the connection. Browser, upload and human steps work from any platform.
What we checked (2026-10-17)
Wave MCP has tools to list and search sessions, and get_transcript returns a full transcript. It can’t edit or delete recordings.
Otter MCP has three tools: Get user info, Search and Fetch. Fetch returns a full transcript. It signs in with OAuth, and you can set permissions for each tool. Otter lists it in Claude’s connectors directory and as a ChatGPT app. We didn’t find a plan requirement.
Julius AI has no MCP server, so you upload the CSV yourself. Julius has a $0 tier. Plus is $16 a month billed annually.
Set it up
Connect Wave or Otter to your AI assistant.
Ask it to fetch each interview and pull out direct quotes into a CSV with one row per quote.
Upload the CSV to Julius and ask for theme counts by interview.
Read the quotes behind each theme in the original transcripts before you write anything up. Speaker labels and paraphrases are where errors creep in.
Sources
Julius AI · Julius AI · official · accessed 2026-10-17
