seed-mcp
Generates natural speech and audio using BytePlus Seed Audio 1.0, providing tools for submission, status checking, voice listing, and model listing.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@seed-mcpGenerate a 30-second voiceover for a podcast intro."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
BytePlus Seed Audio
Generate natural speech and audio with BytePlus Seed Audio 1.0 β from Claude, the terminal, or your own code. Three surfaces over one zero-dependency SDK:
I want to⦠| Use |
Talk to Claude / Claude Code | MCP server ( |
Generate from the terminal | CLI ( |
Claude Code skill | Skill ( |
Build my own integration | SDK ( |
Provider: Seed Audio runs on fal.ai (
bytedance/seed-audio-1.0) today. The SDK hides this behind a provider abstraction, so when BytePlus releases its native Seed Audio API you flipSEED_PROVIDER=byteplus(and addBYTEPLUS_SEED_API_KEY) β nothing else changes. Seeseed/providers/.
Prerequisites
Python 3.10+
A fal.ai API key β set
FAL_KEY(get one at https://fal.ai/dashboard/keys).
Related MCP server: ElevenLabs MCP Server
Install (workspace, for development)
uv sync --all-packages --dev # installs seed-sdk, seed-mcp, seed-cliπ₯ MCP Server
Expose Seed Audio to Claude Desktop / Claude Code.
pip install seed-mcp # or: uv pip install ./packages/seed-mcp
export FAL_KEY=<your-fal-key>
python -m seed_mcp # stdio transport (default)Register it (or use the CLI installer, below). Claude config:
{
"mcpServers": {
"seed": { "command": "python", "args": ["-m", "seed_mcp"] }
}
}Tools
Tool | Purpose |
| Submit an audio job β returns |
| Poll until |
| List preset voice ids |
| List Seed models + capabilities |
| Liveness, provider, credential check |
Hosted / Docker
docker build -t byteplus-seed-mcp .
docker run -e FAL_KEY=<key> -e MCP_TRANSPORT=sse -p 8000:8000 byteplus-seed-mcp
# health: GET http://localhost:8000/healthπ» CLI
pip install seed-cli # or: pip install 'seed-cli[mcp]'
seed auth login # stores FAL_KEY in ~/.seed/credentials
# Generate
seed generate \
--prompt "A short suspense radio drama in a late-night convenience store." \
--watch
# With a preset voice
seed voices # list presets
seed generate -p "Welcome back to the late show." -v sophie_en_zh --watch
# Voice cloning from reference audio
seed generate -p "In @Audio1's voice: 'Once upon a timeβ¦'" \
--audio-ref https://cdn.example.com/narrator.mp3 --watch
# Track a job
seed status <request_id>
seed watch <request_id>
# Skill management (Claude Desktop + Claude Code)
seed skill install
seed skill checkRun seed --help for the full command reference.
π§ Claude Code Skill
skills/seed.md (+ skills/references/) teaches Claude Code how to use Seed Audio well β
prompting, voice presets, cloning, multi-speaker scenes, and safety.
seed skill install # copies the skill + registers the MCP server
# restart Claude Code, then just ask it to "generate a 20s upbeat intro voiceover"π¦ SDK
from seed import SeedClient
client = SeedClient() # provider from SEED_PROVIDER (default: fal)
task = client.submit_audio(
"A short suspense radio drama in a late-night convenience store.",
output_format="mp3",
)
# poll until done
import time
while not (result := client.check_task(task.request_id)).terminal:
time.sleep(5)
print(result.audio_url)seed-sdk has zero runtime dependencies (stdlib urllib only).
Repo structure
byteplus-seed-mcp/
βββ packages/
β βββ seed-sdk/ # core: client, types, credentials, providers/{fal,byteplus}
β βββ seed-mcp/ # FastMCP server (5 tools, stdio + SSE)
β βββ seed-cli/ # Typer + Rich CLI, skill installer
βββ skills/ # seed.md + references/
βββ Dockerfile # SSE server image
βββ render.yaml # Render.com deployment
βββ pyproject.toml # uv workspaceCredentials
Resolution order (first non-empty wins): explicit arg β FAL_KEY env β
~/.seed/credentials [default] β .env.
Release
Independent per-package PyPI publishes via tags:
git tag sdk/v0.1.0 && git push --tags # β seed-sdk
git tag mcp/v0.1.0 && git push --tags # β seed-mcp
git tag cli/v0.1.0 && git push --tags # β seed-cliRoadmap
Native BytePlus Seed Audio provider (
SEED_PROVIDER=byteplus)Local-file upload helper (host local audio/images β public URL)
Additional Seed models as they ship
Support
Seed Audio model: https://fal.ai/models/bytedance/seed-audio-1.0
fal queue API: https://docs.fal.ai/model-endpoints/queue
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/mittulmadaan/byteplus-seed-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server