Modellix
Overview
Modellix is a Model-as-a-Service platform for AI image, video, and speech generation or transcription. This skill teaches agents to use the official modellix-cli workflow (doctor → model run --wait → task download).
Upstream package: https://github.com/Modellix/modellix-plugin/tree/main/skills/modellix (Open Plugins layout; skill tree under skills/modellix/).
When to Use This Skill
- Generate images from text prompts
- Generate or edit videos from text or images
- Generate speech from text, transcribe speech, or transform one voice into another
- Call Modellix models through a unified API/CLI
- The user mentions Modellix, Seedream, Seedance, Nano Banana, Whisper, Qwen Audio, CosyVoice, or similar providers via Modellix
How It Works
- Authenticate with
MODELLIX_API_KEY or modellix-cli auth login
- Run
modellix-cli doctor --json
- Use default models when unspecified (T2I:
google/nano-banana-2-lite, T2V: bytedance/seedance-2.0-mini-t2v, I2I: google/nano-banana-2-lite-edit, I2V: bytedance/seedance-2.0-fast-i2v, V2V: bytedance/seedance-2.0-fast-v2v, TTS: alibaba/qwen-audio-3.0-tts-flash, STT: openai/whisper-1, STS: alibaba/cosyvoice-clone)
- Submit with
modellix-cli model run --wait --json
- Persist outputs with
modellix-cli task download
Examples
Text-to-image
modellix-cli model run \
--model-slug google/nano-banana-2-lite \
--body '{"prompt":"A cinematic sunset over a futuristic city"}' \
--wait --timeout 5m --json
Text-to-video
modellix-cli model run \
--model-slug bytedance/seedance-2.0-mini-t2v \
--body '{"prompt":"Ocean waves under a cloudy sunset"}' \
--wait --timeout 10m --json
Text-to-speech
modellix-cli model run \
--model-slug alibaba/qwen-audio-3.0-tts-flash \
--body '{"text":"There is a large garden behind my house.","voice":"longanhuan_v3.6"}' \
--wait --timeout 5m --json
Speech-to-text
modellix-cli model run \
--model-slug openai/whisper-1 \
--body '{"url":"https://example.com/meeting.mp3"}' \
--wait --timeout 5m --json
Speech-to-speech
modellix-cli model run \
--model-slug alibaba/cosyvoice-clone \
--body '{"model":"cosyvoice-v3.5-plus","url":"https://example.com/reference.wav","text":"There is a large garden behind my house."}' \
--wait --timeout 5m --json
Best Practices
- Prefer CLI
model run --wait over hand-rolled polling
- Before a paid submission, disclose the provider, model, prompt or source media that will leave the machine, expected cost, and output path; obtain explicit user approval
- Prefer session-scoped API-key use; run
modellix-cli auth login only when the user approves persistent local credential storage
- Do not blindly retry paid submissions after unknown outcomes — check
task history
- Confirm the destination and overwrite policy before
task download; never replace an existing file without explicit approval
- Download results before they expire; hosted result URLs are retained for about 7 days
- Fetch request schemas from
model describe docs_url or https://docs.modellix.ai/llms.txt
Security & Safety Notes
- Requires a Modellix API key; never print secrets in logs
- Prompts and uploaded source media leave the machine for
api.modellix.ai and Modellix CDN processing
- Paid generation consumes account balance and must not be submitted or retried without the approval described above
Limitations
- Requires a Modellix account, network access, a valid API key, and sufficient account balance.
- Model availability, request schemas, pricing, quotas, moderation, and generation time are controlled by Modellix and may change.
- Generated outputs require human review for quality, rights, privacy, and policy compliance before publication.
- This skill documents the CLI workflow only; it does not define a REST fallback or guarantee that a completed remote task downloads successfully.
1---2name: modellix3description: "Integrate the Modellix API/CLI for async AI image, video, and speech generation or transcription (model run --wait, task download)."4category: creative5risk: critical6source: community7source_repo: Modellix/modellix-plugin8source_type: official9date_added: "2026-07-16"10author: Modellix11tags: [image-generation, video-generation, audio-generation, text-to-speech, speech-to-text, speech-to-speech, modellix, cli, api]12tools: [claude, cursor, gemini]13license: "MIT"14license_source: "https://github.com/Modellix/modellix-plugin/blob/main/LICENSE"15metadata:16 source: https://skillmd.com/skills/mhassan0000/modellix17---1819# Modellix2021## Overview2223Modellix is a Model-as-a-Service platform for AI image, video, and speech generation or transcription. This skill teaches agents to use the official `modellix-cli` workflow (doctor → model run --wait → task download).2425Upstream package: https://github.com/Modellix/modellix-plugin/tree/main/skills/modellix (Open Plugins layout; skill tree under `skills/modellix/`).2627## When to Use This Skill2829- Generate images from text prompts30- Generate or edit videos from text or images31- Generate speech from text, transcribe speech, or transform one voice into another32- Call Modellix models through a unified API/CLI33- The user mentions Modellix, Seedream, Seedance, Nano Banana, Whisper, Qwen Audio, CosyVoice, or similar providers via Modellix3435## How It Works36371. Authenticate with `MODELLIX_API_KEY` or `modellix-cli auth login`382. Run `modellix-cli doctor --json`393. Use default models when unspecified (T2I: `google/nano-banana-2-lite`, T2V: `bytedance/seedance-2.0-mini-t2v`, I2I: `google/nano-banana-2-lite-edit`, I2V: `bytedance/seedance-2.0-fast-i2v`, V2V: `bytedance/seedance-2.0-fast-v2v`, TTS: `alibaba/qwen-audio-3.0-tts-flash`, STT: `openai/whisper-1`, STS: `alibaba/cosyvoice-clone`)404. Submit with `modellix-cli model run --wait --json`415. Persist outputs with `modellix-cli task download`4243## Examples4445### Text-to-image4647```bash48modellix-cli model run \49 --model-slug google/nano-banana-2-lite \50 --body '{"prompt":"A cinematic sunset over a futuristic city"}' \51 --wait --timeout 5m --json52```5354### Text-to-video5556```bash57modellix-cli model run \58 --model-slug bytedance/seedance-2.0-mini-t2v \59 --body '{"prompt":"Ocean waves under a cloudy sunset"}' \60 --wait --timeout 10m --json61```6263### Text-to-speech6465```bash66modellix-cli model run \67 --model-slug alibaba/qwen-audio-3.0-tts-flash \68 --body '{"text":"There is a large garden behind my house.","voice":"longanhuan_v3.6"}' \69 --wait --timeout 5m --json70```7172### Speech-to-text7374```bash75modellix-cli model run \76 --model-slug openai/whisper-1 \77 --body '{"url":"https://example.com/meeting.mp3"}' \78 --wait --timeout 5m --json79```8081### Speech-to-speech8283```bash84modellix-cli model run \85 --model-slug alibaba/cosyvoice-clone \86 --body '{"model":"cosyvoice-v3.5-plus","url":"https://example.com/reference.wav","text":"There is a large garden behind my house."}' \87 --wait --timeout 5m --json88```8990## Best Practices9192- Prefer CLI `model run --wait` over hand-rolled polling93- Before a paid submission, disclose the provider, model, prompt or source media that will leave the machine, expected cost, and output path; obtain explicit user approval94- Prefer session-scoped API-key use; run `modellix-cli auth login` only when the user approves persistent local credential storage95- Do not blindly retry paid submissions after unknown outcomes — check `task history`96- Confirm the destination and overwrite policy before `task download`; never replace an existing file without explicit approval97- Download results before they expire; hosted result URLs are retained for about 7 days98- Fetch request schemas from `model describe` `docs_url` or https://docs.modellix.ai/llms.txt99100## Security & Safety Notes101102- Requires a Modellix API key; never print secrets in logs103- Prompts and uploaded source media leave the machine for `api.modellix.ai` and Modellix CDN processing104- Paid generation consumes account balance and must not be submitted or retried without the approval described above105106## Limitations107108- Requires a Modellix account, network access, a valid API key, and sufficient account balance.109- Model availability, request schemas, pricing, quotas, moderation, and generation time are controlled by Modellix and may change.110- Generated outputs require human review for quality, rights, privacy, and policy compliance before publication.111- This skill documents the CLI workflow only; it does not define a REST fallback or guarantee that a completed remote task downloads successfully.