Skill: text-to-speech

Version: 1.0.0

Convert text to speech using OpenAI TTS.

Outputs audio in various formats (mp3, wav, opus).

name: text-to-speech version: 1.0.0 description: Convert text to speech using AI (mp3, wav, opus output)

Credentials

credentials:

• name: OPENAI_API_KEY required: true description: OpenAI API key for TTS

Skill inputs

inputs:

• name: text type: string required: true description: Text to convert to speech (max 4096 chars)
• name: voice type: string default: alloy enum: [alloy, echo, fable, onyx, nova, shimmer] description: Voice to use
• name: format type: string default: mp3 enum: [mp3, opus, aac, flac, wav, pcm] description: Audio output format

Skill outputs

outputs:

• name: audio type: binary description: Audio file content (base64 encoded)
• name: metadata type: object description: Generation metadata

Backend options

backends:

• name: openai type: remote requires: [OPENAI_API_KEY] description: OpenAI TTS-1 (~$0.015 per 1K chars)

Expanso components used

components: inputs: - stdin - http_server processors: - mapping - openai_speech - log outputs: - stdout - sync_response