Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add sonicfieldlabs/akouo --skill voice-speech-listeninggit clone --depth 1 https://github.com/sonicfieldlabs/akouoWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sonicfieldlabs/akouo/voice-speech-listening)<a href="https://agentmods.dev/skills/sonicfieldlabs/akouo/voice-speech-listening"><img src="https://agentmods.dev/badge/skills/sonicfieldlabs/akouo/voice-speech-listening/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sonicfieldlabs/akouo/voice-speech-listening"><img src="https://agentmods.dev/badge/skills/sonicfieldlabs/akouo/voice-speech-listening.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00176 | $0.02278 |
| Opus 5 | $0.00088 | $0.01139 |
| Sonnet 5 | $0.00035 | $0.00456 |
| Haiku 4.5 | $0.00018 | $0.00228 |
Grade A, and why
voice-speech-listening scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
voice-speech-listening
Purpose
voice-speech-listening is the ear for voice as sound, speech, body, interface, trace, performance, and data. It separates vocal qualities from speaker identity, transcript content, emotion, intention, consent, and technical mediation.
This mode exists because agents often overclaim around voice. A transcript is not the voice. A voice is not proof of identity. Prosody is not direct access to feeling. A synthetic voice is not evidence of a real speaker.
When To Use
Use this skill for:
- spoken voice, singing voice, chant, breath, whisper, shout, and vocal texture
- podcasts, radio, oral history, testimony, film voice, dubbing, and game dialogue
- ASR transcripts, captions, diarization, speaker labels, and speech-to-text outputs
- synthetic voice, voice cloning, TTS, voice agents, and speech-native models
- accent, dialect, intelligibility, prosody, pacing, turn-taking, interruption, and latency
- acousmatic voice, object-voice, offscreen voice, and disembodied speech
- identity, consent, provenance, labor, accessibility, or surveillance questions involving voice
Core Question
What can be responsibly said about this voice or speech without collapsing sound into identity, transcript, emotion, intention, or machine output?
Conceptual Refinements
- Voice is not speech, and speech is not text: vocal sound, linguistic content, and transcript are three different evidentiary objects.
- The acousmatic voice and object-voice show that a voice can exceed or escape its visible body; disembodiment is a listening relation, not proof of identity or presence.
- Prosody, accent, and grain are heard qualities, not windows into emotion, sincerity, health, or demographic category.
- ASR, diarization, TTS, voice cloning, and speech-native agents are distinct systems with distinct failure modes; never attribute one system's behavior to another.
- Voice is also data: consent, provenance, ownership, and deployment context condition every claim about recorded or synthetic voices.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/claim-taxonomy.schema.json 5.3 KB
- references/ensemble.schema.json 1.8 KB
- references/listening-context.schema.json 7.7 KB
- references/listening-output.schema.json 11 KB
- references/listening-pass.schema.json 2.4 KB
- references/listening-provenance.schema.json 3.9 KB
- references/route-decision.schema.json 1.8 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 148 lines · 176 tokens per session scan A 7ea229db49b3
voice-speech-listening is a skill published in the GitHub repository sonicfieldlabs/akouo (10 stars, last pushed 1mo ago), licensed MIT. It adds 176 tokens to every session and 2,278 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…