Create Speech

Generates audio from the input text

Request Body

modelstring

TTS model ID

inputstring

Text to generate audio for. Max 4096 characters.

Lengthlength <= 4096

voicestring

Voice to use. Options: alloy, ash, ballad, coral, echo, fable, nova, onyx, sage, shimmer, verse

response_format?string

Audio output format

Default"mp3"

Value in"mp3" | "opus" | "aac" | "flac" | "wav" | "pcm"

speed?number

Speed of generated audio (0.25 to 4.0)

Default1

Range0.25 <= value <= 4

instructions?string

Natural language instructions for voice tone/emotion. Only supported by gpt-4o-mini-tts.

Response Body

curl -X POST "https://api.osmapi.com/v1/audio/speech" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-1",
    "input": "string",
    "voice": "alloy"
  }'

curl -X POST "https://api.osmapi.com/v1/audio/speech" \  -H "Content-Type: application/json" \  -d '{    "model": "tts-1",    "input": "string",    "voice": "alloy"  }'

Empty

How is this guide?

Create Speech

Request Body

Response Body

200