# Hume's Audio Decision API answers plain-language questions about a recording with probabilities, no transcript

Canonical: https://theagenticweekly.com/news/hume-audio-decision-api · Evidence: Reported · First seen: 2026-11-03 13:01 UTC · Source published: not stated by the source · Brief published: 2026-11-03 13:07 UTC · Updated: 2026-11-03 13:07 UTC · Author: Agentic Weekly

> Hume's Audio Decision API, launched November 2, 2026, takes one audio file and questions written in plain language and returns probabilities instead of text. Hume's docs say it "returns no transcript, reply or explanation". Pricing is $0.47 per 1M input tokens; access starts from a waitlist.

## What changed

- Hume's changelog dates the launch November 2, 2026: one endpoint, POST /v0/decisions/file, answers all your questions about one audio file in one request.
- Each question uses one of four answer types: noul (yes/no), choice, score (a rating scale) or span (start and end times in the clip, for example where someone laughs).
- Input is one MP3 or WAV file between 5 seconds and 5 minutes, plus an optional context field describing the recording; several recordings mean one request per file.
- Billing is $0.47 per 1M input tokens (the audio plus the text of your questions); answers are not billed, and an organization gets a one-time 1M-token trial credit once access is granted.
- There are Python (hume-audio-decisions) and TypeScript (@humeai/audio-decisions) SDKs, plus endpoints to estimate input tokens before a run and to list past runs.

## Who it matters for

Teams building or testing voice agents, and anyone who scores call recordings. Hume lists evaluating text-to-speech output, testing voice agents, reviewing support calls and labeling speech corpora as the intended uses. Because the answer is a probability rather than text, your own code sets the threshold, for example flag a call when the chance the caller sounds frustrated passes 0.8.

It does not replace speech-to-text: it returns no transcript. Hume's own example pairs its answers with a separate transcription before handing both to an LLM that applies business rules. Live, real-time use is described by Hume as a longer-term opportunity; today's API takes recorded clips of 5 seconds to 5 minutes.

## In the source's words

> "It returns no transcript, reply or explanation; your code does the reasoning with the numbers."
> (Hume Audio Decisions API docs, overview, https://dev.hume.ai/audio-decisions/docs/overview)

> "Raw audio goes in, an answer with a confidence score comes out, structured and ready for your code or your agent to act on."
> (Hume blog, Introducing Hume's Audio Decision API, https://www.hume.ai/blog/introducing-hume-audio-decision-api)

## What we have not verified

- We have not run the API; access is through a waitlist.
- The 70.7% agreement with a human panel's average judgment (versus 56.5% for a single rater) is Hume's own initial evaluation; the test set is not published.
- Speed and accuracy comparisons against other models are Hume's claims and were not checked.
- Pricing is as listed on Hume's billing page on November 3, 2026.

## Timeline

- Source published: not stated by the source
- First seen by our watcher: 2026-11-03 13:01 UTC (via X news search (daily release scan))
- Brief published: 2026-11-03 13:07 UTC

## Sources

- [Hume blog: Introducing Hume's Audio Decision API (Nov 2, 2026)](https://www.hume.ai/blog/introducing-hume-audio-decision-api) (primary source) (fetched 2026-11-03)
- [Hume Audio Decisions API docs: overview](https://dev.hume.ai/audio-decisions/docs/overview) (primary source) (fetched 2026-11-03)
- [Hume Audio Decisions API docs: billing](https://dev.hume.ai/audio-decisions/docs/billing) (primary source) (fetched 2026-11-03)
- [Hume Audio Decisions API changelog](https://dev.hume.ai/audio-decisions/changelog) (primary source) (fetched 2026-11-03)

## Related

- [Vapi: verdict and setup guide](https://theagenticweekly.com/tools/vapi)
- [Retell AI: verdict and setup guide](https://theagenticweekly.com/tools/retell)
- [Deepgram: verdict and setup guide](https://theagenticweekly.com/tools/deepgram)
- [ElevenLabs: verdict and setup guide](https://theagenticweekly.com/tools/elevenlabs)
- [All news briefs](https://theagenticweekly.com/news)
- [This week's releases](https://theagenticweekly.com/this-week)
- [New AI models this week](https://theagenticweekly.com/models/this-week)

## How to cite

Agentic Weekly, "Hume's Audio Decision API answers plain-language questions about a recording with probabilities, no transcript", published 2026-11-03 13:07 UTC, https://theagenticweekly.com/news/hume-audio-decision-api