IntegrationsAudio generation · built in
Music, sound and speech.One balance.
Audio generation gives Claude Code, Codex, Cursor or any MCP agent dozens of hosted music, sound effect and speech models through CoreSpeed, with no account or API key of their own. Your agent reads a model's rate, then makes a score, a sound effect or a voice-over from text. Each file lands in your organization's Drive.
A score, a cue,a voice.
Requests you can make right after setup. The data is fictional.
Cursor for youDone
media__generate
A 30-second instrumental is in your Drive, with a link that works for 12 hours.
Score a short video
One track in your Drive
- A whoosh for the logoSound effect model
- Asked forA soft whoosh, under one second
- ResultOne short audio file
Make a sound effect
Each model has its own rate
- A narrator from a voice librarySpeech + Fish Audio
- VoiceA licensed library voice
- OrA new voice from a description
Pick a voice for the voice-over
Fish Audio's voices, the same tool
Describe the sound.Get the file.
Your agent finds a music, sound or speech model, reads its rate, and runs it. The audio comes back as a link and as a file in your Drive.
Reads fromAudio generation
How media generation works →Make a 30-second upbeat instrumental for our launch video, with light percussion and no vocals. Show me the model's rate before you run it.
media__list_modelsok
Music models, each with a rate
Keep your agent.Nothing to connect.
One CoreSpeed account, across compatible agents.
- 1
Set up CoreSpeed
Give your agent the setup line. It adds CoreSpeed and signs you in.
- 2
Check the price
Every tool has a rate in credits. Your agent reads it before each call.
- 3
Start with one task
Ask for one short track or sound, and ask your agent for the rate first.
Setup guidesClaude CodeCodexCursor