Generate OpenAI-Compatible Voice ≤500 chars

OpenAI-compatible text-to-speech endpoint (input, voice, response_format) for drop-in use with code already built against the OpenAI TTS API, 1 of 10 standard voices, up to 500 characters, WAV/FLAC/OGG output. Use it to: swap OpenAI TTS calls for a pay-per-call x402 alternative, generate speech from an existing OpenAI-style client, avoid API-key management for short text-to-audio requests. USDC on Base.

post/v1/audio/speech

Request

  • Base URL: https://voice.forgemesh.io
  • URL: https://voice.forgemesh.io/v1/audio/speech
  • Auth: none declared

Request body

inputstring required

OpenAI-compatible input text. Use non-long route for 1-500 chars and -long route for 501-2000 chars.

voice'M1' | 'M2' | 'M3' | 'M4' | 'M5' | 'F1' | 'F2' | 'F3' | 'F4' | 'F5'

Standard voice: M1-M5 or F1-F5

modelstring

Optional compatibility field; ForgeMesh Voice is always used

response_format'wav' | 'flac' | 'ogg'

Requested audio format

Response

Successful synthesis response

Changes

No recorded changes to this operation across all 1 revision of this API.