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 joeVenner/awesome-minimax-h3 --skill minimax-speechgit clone --depth 1 https://github.com/joeVenner/awesome-minimax-h3Wrote 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/joevenner/awesome-minimax-h3/minimax-speech)<a href="https://agentmods.dev/skills/joevenner/awesome-minimax-h3/minimax-speech"><img src="https://agentmods.dev/badge/skills/joevenner/awesome-minimax-h3/minimax-speech/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/joevenner/awesome-minimax-h3/minimax-speech"><img src="https://agentmods.dev/badge/skills/joevenner/awesome-minimax-h3/minimax-speech.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 | $0.00215 | $0.04385 |
| Opus 5 | $0.00108 | $0.02193 |
| Sonnet 5 | $0.00043 | $0.00877 |
| Haiku 4.5 | $0.00021 | $0.00439 |
Grade A, and why
minimax-speech scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
compatibility: Requires a MiniMax platform API key (https://platform.minimax.io), curl, jq, and ffmpeg for post-processing How it starts
The opening of the file, as written. The whole thing — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MiniMax Speech — Cloud Text-to-Speech, Voice Cloning & Voice Design
This skill covers the CLOUD platform API only (api.minimax.io, Bearer auth with a
platform API key). It does not cover the local Electron gateway — see minimax-local-audio
for that, and do not mix their parameter shapes: this API uses real JSON types
("speed": 0.9), the local gateway uses strings ("speed": "1").
Quick start
curl -s -X POST "https://api.minimax.io/v1/t2a_v2" \
-H "Authorization: Bearer $MINIMAX_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "speech-2.8-hd",
"text": "The text to speak.",
"output_format": "url",
"language_boost": "English",
"voice_setting": {"voice_id": "English_CaptivatingStoryteller", "speed": 0.9, "vol": 1, "pitch": 0, "emotion": "calm"},
"audio_setting": {"sample_rate": 44100, "bitrate": 256000, "format": "wav", "channel": 1}
}' | jq -r '.data.audio' | xargs curl -sL -o narration.wav
No GroupId parameter is needed. The call is synchronous — audio comes back in one response.
Phase 0: Choose the approach
| Need | Use |
|---|---|
| Any script under 10 000 characters | Sync /v1/t2a_v2 — simplest, returns audio directly |
| Long-form (audiobook, > 10 000 chars, up to 1M) | Async /v1/t2a_async_v2 — see async reference |
| Real-time / low latency playback | "stream": true, or the WebSocket endpoint |
| A voice that matches a real person's sample | Voice cloning — Phase 5 |
| A specific timbre with no sample to work from | Voice design — Phase 6, describe it in words |
For voiceover against picture, always use the sync endpoint and render each line as its own call. See Phase 4 — this is the single most important technique in this skill.
Phase 1: Pick the model
| Model | Character |
|---|---|
speech-2.8-hd |
Best quality. Supports interjection tags. Default choice for narration. |
speech-2.8-turbo |
Faster, natural flow |
speech-2.6-hd |
Ultra-low latency, enhanced naturalness |
speech-2.6-turbo |
Faster, cheaper, good for agents |
speech-02-hd / speech-02-turbo |
Superior rhythm and stability |
speech-01-hd / speech-01-turbo |
Legacy |
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.
- 12d ago First seen · 366 lines · 0 tokens per session scan A c44ac1a5f38a
minimax-speech is a skill published in the GitHub repository joeVenner/awesome-minimax-h3 (9 stars, last pushed 26d ago), licensed MIT. It adds 215 tokens to every session and 4,385 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
minimax-cli
Nested swiss-knife reference for the MiniMax mmx CLI and the canonical MiniMax CLI procedure shipped with the TUI: install mmx-cli, discover the correct TUI-managed MiniMax preset/key slot without leaking secrets, match mainland vs international regions, and route image/video/music/TTS generation or one-shot shell…
videoagent-video-studio
Generate short AI videos from text or images — text-to-video, image-to-video, and reference-based generation — with zero API key setup. Use when the user wants to create a video clip, animate an image, or generate video from a description.
evo-video-filler-word-remover
Detects filler words in video/audio interviews using ASR (faster-whisper) with word-level timestamps, saves annotations as JSON, and extracts filler clips into a compilation video.
evo-threejs-obj-export
Generates a Node.js ES module script that dynamically imports a Three.js object definition file, constructs a scene graph, applies a -90 deg X-rotation for Y-up to Z-up coordinate conversion (Blender compatibility), forces world matrix updates, serializes the scene to Wavefront OBJ format using OBJExporter, and writes…
evo-threejs-to-obj
Convert Three.js scene graphs to Wavefront OBJ format suitable for Blender (Z-up coordinate system). Handles InstancedMesh, nested hierarchies, coordinate transforms, and headless Node.js execution.
evo-video-tutorial-indexer
A comprehensive skill for extracting chapter indices from tutorial videos using FFmpeg audio extraction, OpenAI Whisper ASR transcription with word-level timestamps, and semantic chapter alignment via fuzzy string matching.