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 yoav0gal/agent-voice --skill spoken-responsegit clone --depth 1 https://github.com/yoav0gal/agent-voiceWrote 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/yoav0gal/agent-voice/spoken-response)<a href="https://agentmods.dev/skills/yoav0gal/agent-voice/spoken-response"><img src="https://agentmods.dev/badge/skills/yoav0gal/agent-voice/spoken-response/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/yoav0gal/agent-voice/spoken-response"><img src="https://agentmods.dev/badge/skills/yoav0gal/agent-voice/spoken-response.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 | $0.00034 | $0.00522 |
| Opus 5 | $0.00017 | $0.00261 |
| Sonnet 5 | $0.00007 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
spoken-response 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 8d 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.
This is a copy
86% identical to spoken-response-controls — 13 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spoken Response
A spoken response reads the assistant response aloud without rewriting it.
Mode
Choose the mode from the user's request:
Single— create audio for the current response. This is the default.Previous— create audio for the most recent assistant response and return a brief confirmation.Thread— create audio for the current and later responses until disabled or the thread ends.
Respond
-
Select the response:
- For
SingleandThread, finalize the current response. - For
Previous, use the most recent assistant response.
- For
-
Set
RESPONSE_AS_TEXTto a read-aloud copy:- Fidelity: preserve wording and order; do not summarize or rephrase.
- Non-prose: translate formatting and read tables naturally. Explain code or visuals when useful; otherwise briefly introduce them ("Here is the code" or "See the diagram below") and continue.
-
Set
LABELtoSR. When a thread title is already available, use<title> - SR. -
Create the recording with the configured voice, speed, and format:
agent-voice speak "$RESPONSE_AS_TEXT" --label "$LABEL"For long responses, create a unique file in the system temporary directory. The operating system handles cleanup.
agent-voice speak --label "$LABEL" < "$RESPONSE_AS_TEXT_FILE" -
Place the audio above the written response or
Previousconfirmation using default.md immediately afterspeakreturns a receipt with generation.state: "started"
For speaker playback, add -p and continue after the result reports
playback.state: "started". Add --play-after SECONDS to schedule it without
blocking. On synthesis failure, send the written response with a brief
failure note.
Setup
If agent-voice is unavailable:
uv tool install agent-voice
agent-voice setup
Resources
- CLI help:
agent-voice --help - Source and docs: Agent Voice on GitHub
What ships with it
2 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.
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.
- 8d ago First seen · 67 lines · 34 tokens per session scan A 054cad8e28ef
spoken-response is a skill published in the GitHub repository yoav0gal/agent-voice (11 stars, last pushed 20d ago), licensed MIT. It adds 34 tokens to every session and 522 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to spoken-response-controls, differing in 13 lines, and is treated as a copy.
Other skills, from other repositories
podcast
Use when planning, recording, editing or publishing one podcast episode end to end — the run-of-show and guest brief, recording settings, the loudness master, the Podcasting 2.0 sidecars for chapters and transcripts, the RSS item, and timestamped SEO show notes. Covers audio that is quiet on one platform and loud on…
audiobook-maker
A workflow for turning long text, novels, and reports into spoken audio files. Text longer than 3,000 Chinese characters is split into smaller sections before speech is generated.
atet
Use Atet to create, generate, record, edit, and render visual media with a local CLI and coding agent. Trigger for AI image or video generation, screen, camera, microphone, or system-audio recording, non-destructive video editing, silence and filler-word removal, captions or subtitles, speaker framing, screen zooms…
c-video
Download videos, extract audio, convert formats, and clip segments using yt-dlp and ffmpeg. Supports YouTube, Vimeo, and hundreds of other sites.
c-music
Control Spotify playback using the spogo CLI. Play, pause, skip, search tracks/albums/playlists, manage the queue, and browse your library.
media-gen
Hub üzerinden ComfyUI ile medya üretimi — görsel, video, görsel düzenleme (ses/3D eklenecek). Bir iş için görsel/video gerektiğinde (UI asset, blog kapağı, animasyon, test medyası) agent kendisi üretir. Workflow seçimi, placeholder kullanımı ve hata ayıklama.