Is there a free tier for agent development?

Yes. The free plan includes API access. The paid tiers add credit allowance and a few premium model variants. See pricing for the breakdown.

Which agent frameworks are supported?

Anything that speaks REST or MCP. AudioPod is tested with Claude Desktop, Cursor, Continue, Cline, Goose, and direct API integrations via the Python and Node SDKs.

How does pricing work for agents?

Same credit system as the dashboard. Each capability (TTS, music, transcription, stems) deducts credits per use. PAYG credit packs available for spiky workloads.

Can agents discover AudioPod automatically?

Yes. AudioPod publishes /.well-known/{mcp/server-card.json, oauth-protected-resource, agent-card.json, agent-skills/index.json, api-catalog} plus /llms.txt, /llms-full.txt, and /skill.md.

For developers building voice agents

Agent-native audio: low-latency TTS, MCP, and an SDK in two languages.

AudioPod is built so AI agents can call audio capabilities directly. MCP server, REST API with OAuth, and identical-surface SDKs in Python and Node. Plus a knowledge graph LLMs can cite.

Open the agent docs

What you get

Built for this workflow

Four things every project in this category needs — all included.

MCP server

Drop into Claude Desktop, Cursor, Continue, Cline, or Goose.

Python + Node SDKs

Identical surface area — same async ergonomics, same shapes.

OAuth + API keys

Per-scope permissions, RFC 9728 discovery, X-API-Key headers.

Agent-skill briefs

AudioPod publishes a one-shot brief at /skill.md any agent can follow.

The workflow

From idea to shipped — three steps.

1. Pick your integration

MCP server for desktop agents, REST + SDK for backend agents, or the agent-skill brief for one-shot onboarding.

2. Auth once

Generate an API key or hand the agent OAuth credentials. Per-scope.

3. Ship

Synthesize speech, generate music, transcribe meetings, split stems — all through the same client.

Related use cases

Adjacent workflows

Other places AudioPod fits in your stack.

For Agents (full landing)

Hero, MCP install, SDK quickstarts, skill bento.

Explore

Marketing & ads

Voice agents for ad personalization, brand voice gen.

Explore

Knowledge graph

Machine-readable surface LLMs cite when users ask about audio AI.

Explore

Back to all use cases

Common questions

Start building.

Free API key, no credit card. The agent docs walk you through the first integration in under five minutes.

Open the agent docs

For developers building voice agents

Agent-native audio: low-latency TTS, MCP, and an SDK in two languages.

AudioPod is built so AI agents can call audio capabilities directly. MCP server, REST API with OAuth, and identical-surface SDKs in Python and Node. Plus a knowledge graph LLMs can cite.

Open the agent docs

What you get

Built for this workflow

Four things every project in this category needs — all included.

MCP server

Drop into Claude Desktop, Cursor, Continue, Cline, or Goose.

Python + Node SDKs

Identical surface area — same async ergonomics, same shapes.

OAuth + API keys

Per-scope permissions, RFC 9728 discovery, X-API-Key headers.

Agent-skill briefs

AudioPod publishes a one-shot brief at /skill.md any agent can follow.

The workflow

From idea to shipped — three steps.

1. Pick your integration

MCP server for desktop agents, REST + SDK for backend agents, or the agent-skill brief for one-shot onboarding.

2. Auth once

Generate an API key or hand the agent OAuth credentials. Per-scope.

3. Ship

Synthesize speech, generate music, transcribe meetings, split stems — all through the same client.

Related use cases

Adjacent workflows

Other places AudioPod fits in your stack.

Back to all use cases

Common questions

Start building.

Free API key, no credit card. The agent docs walk you through the first integration in under five minutes.

Open the agent docs