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 calesthio/generative-media-skills --skill byteplus-seed-speech-ttsgit clone --depth 1 https://github.com/calesthio/generative-media-skillsWrote 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/calesthio/generative-media-skills/byteplus-seed-speech-tts)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/byteplus-seed-speech-tts"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/byteplus-seed-speech-tts/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/calesthio/generative-media-skills/byteplus-seed-speech-tts"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/byteplus-seed-speech-tts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00091 | $0.02976 |
| Opus 5 | $0.00046 | $0.01488 |
| Sonnet 5 | $0.00018 | $0.00595 |
| Haiku 4.5 | $0.00009 | $0.00298 |
Grade A, and why
byteplus-seed-speech-tts 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 9d 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BytePlus Seed Speech TTS
Use this skill for the international BytePlus Seed Speech service. The current documented API host is in the ap-southeast-1.bytepluses.com domain. Do not transfer credentials, endpoints, prices, voice IDs, or commercial assumptions from mainland-China Volcengine Doubao Speech.
Verification and evidence
- Documented fact: behavior stated in official BytePlus documentation or its applicable legal pages.
- Production heuristic: a practical workflow that must be tested with the selected account, voice, and protocol.
- Empirical observation: output measured from an actual dated request.
Provider facts were verified 2026-07-12. Voice inventory, language compatibility, pricing, free quota, concurrency, endpoints, retention, and protocol behavior are volatile. Re-check the official voice list, API page, console, pricing, order form, and DPA immediately before production.
Boundary and taxonomy
BytePlus calls the international product Seed Speech. Current synthesis resource families include:
seed-tts-1.0: TTS 1.0;seed-tts-2.0: TTS 2.0;seed-icl-1.0: authorized Voice Replication 1.0 synthesis;seed-icl-2.0: authorized Voice Replication 2.0 synthesis.
Seed-TTS research papers describe model research and are not API contracts. Do not expose research variants as hosted model IDs.
This leaf covers prebuilt TTS and synthesis with a voice already enrolled and authorized. Voice enrollment itself requires a separate consent, data, and lifecycle review. It does not cover ASR, speech-to-speech agents, interpretation, podcasts, or mainland Volcengine APIs.
Select model family and protocol
TTS 1.0
Use when a chosen voice or required feature is documented for TTS 1.0, especially where the selected protocol documents timestamp or voice-specific emotion support. Do not assume TTS 1.0 and 2.0 voices share identifiers or controls.
TTS 2.0
BytePlus documents broader multilingual and contextual/instruction control. context_texts can give natural-language performance direction; only the first list value is documented as effective. section_id can connect prior synthesis context, with current documentation describing up to 30 rounds or ten minutes.
What ships with it
1 file 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.
- 9d ago First seen · 225 lines · 91 tokens per session scan A 0dfde16248c6
byteplus-seed-speech-tts is a skill published in the GitHub repository calesthio/generative-media-skills (170 stars, last pushed 2mo ago), licensed MIT. It adds 91 tokens to every session and 2,976 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
cliptalk-cover-director
Produces evidence-backed cover candidates and reviewable cover variants for a ClipTalk video. Use when the user asks for a cover, poster frame, thumbnail, or multiple cover directions; do not use for timeline editing or social-video reframing.
cliptalk-smart-reframe
Creates a subject-aware, time-varying crop track and a review-only social-format preview from an accepted ClipTalk cut. Use for automatic vertical, square, or portrait reframing; do not use for a fixed manual crop or before content editing is accepted.
cliptalk-content-extractor
Locates and assembles source passages matching a semantic request. Use for extracting explanations, topics, quotes, demonstrations, or other specifically described content.
cliptalk-interview-editor
Produces a coherent interview edit by combining speaker discovery, topic selection, dialogue context, cleanup, subtitles, and preview. Use for interviews, podcasts, testimonials, or question-and-answer recordings.
cliptalk-shortform-hook-director
Finds and assembles a reviewable short-form cut with a strong opening hook. Use for Shorts, Reels, social clips, talking-head cutdowns, or requests for a punchier opening.
cliptalk-social-reframe-exporter
Creates a review-only 9:16, 4:5, 1:1, or 16:9 version from an existing accepted ClipTalk cut, then checks the rendered preview. Use only when a cut already exists and the user asks to adapt it for Shorts, Reels, Douyin, Xiaohongshu, WeChat Channels, or square feeds; do not use when the user still needs content found…