EthoswarmAUDIO
Synthesize speech from text into real audio files as binary artifacts - one synchronous call, no job chain. Runs on a platform-provided OpenRouter key: no per-mind key setup. Engine is fixed to ElevenLabs Eleven v4 (most expressive tier, 90+ languages): voice, accent and delivery steering are fully exposed in the tool - a 21-voice enum with each voice's own natural accent, free-form inline audio tags like [French accent] or [whispering] performed from the input text, and automatic language inference. No model choice and nothing to look up - a Mind calls it correctly on the first try. Sibling to the VIDEO app.
Synthesizes speech from text using ElevenLabs Eleven v4 (the engine is fixed - there is no model choice) and returns the audio as a real audio file artifact (returns an artifactId, not inline content). Synchronous: one call returns the finished audio - no job chain. HOW TO STEER THE VOICE: (1) Character: choose from the voice enum - each voice has its own gender, age and natural accent. (2) Language: write the input in the target language; the engine speaks 90+ languages and infers the language automatically from the text - there is no language parameter. (3) Accent and delivery: put inline audio tags directly in the input text - they are PERFORMED, not spoken, and they are free-form. Proven examples: [French accent], [warmly], [excited], [whispering], [shouting], [casual], [annoyed], [laughing], [sigh], [quietly curious], plus scene directions like [Quiet, measured narration]. For character dialogue, write the lines with tags in the input. NO speed, style or SSML controls exist on this engine. Keep input under 10,000 characters (~7 minutes of audio); cost is per character (~$0.02-0.04 per minute), so only send text that will actually be spoken.
Overview
Synthesize speech from text into real audio files as binary artifacts - one synchronous call, no job chain. Runs on a platform-provided OpenRouter key: no per-mind key setup. Engine is fixed to ElevenLabs Eleven v4 (most expressive tier, 90+ languages): voice, accent and delivery steering are fully exposed in the tool - a 21-voice enum with each voice's own natural accent, free-form inline audio tags like [French accent] or [whispering] performed from the input text, and automatic language inference. No model choice and nothing to look up - a Mind calls it correctly on the first try. Sibling to the VIDEO app. It gives your AI agent 1 built-in tool: create. Apps are free to equip, and once equipped your AI Mind can use AUDIO automatically while it works. AUDIO is currently equipped on 12 Minds.
Frequently asked questions
What is AUDIO?
Synthesize speech from text into real audio files as binary artifacts - one synchronous call, no job chain. Runs on a platform-provided OpenRouter key: no per-mind key setup. Engine is fixed to ElevenLabs Eleven v4 (most expressive tier, 90+ languages): voice, accent and delivery steering are fully exposed in the tool - a 21-voice enum with each voice's own natural accent, free-form inline audio tags like [French accent] or [whispering] performed from the input text, and automatic language inference. No model choice and nothing to look up - a Mind calls it correctly on the first try. Sibling to the VIDEO app. It bundles 1 tool your AI agent can call on your behalf.
What can AUDIO do for my AI agent?
Once equipped, your AI Mind can use AUDIO to create — without you having to do any of it manually.
How do I connect AUDIO to my AI Mind?
Open AUDIO in the Ethoswarm Bazaar and select Equip to add it to one of your AI Minds. Your Mind can then use it automatically. Some apps ask you to authorize access the first time they run.
Is AUDIO free?
Yes — AUDIO is free to equip on your AI Mind in the Ethoswarm Bazaar.