Skip to main content

​
POST /v1/audio/speech

Converts text into natural-sounding speech. The response is a binary audio stream in the requested format. This endpoint maps to the createSpeech operation and is compatible with the OpenAI TTS API.

​
Request headers

​
x-portkey-provider
string
The provider to route the request to (e.g. openai). Required when not using a config.
​
x-portkey-api-key
string
Your provider API key.
​
x-portkey-config
string
A JSON config object or config ID that defines routing, fallbacks, retries, and more.
​
x-portkey-virtual-key
string
A virtual key ID from Portkey Cloud.

​
Request body

​
model
string
required
The TTS model to use. OpenAI supports tts-1 (optimized for speed) and tts-1-hd (optimized for quality).
​
input
string
required
The text to convert to speech. Maximum 4096 characters.
​
voice
string
required
The voice to use. OpenAI provides alloy, ash, coral, echo, fable, onyx, nova, and shimmer. Check your provider’s documentation for available voices.
​
response_format
string
default:"mp3"
The audio output format. Supported values: mp3, opus, aac, flac, wav, pcm.
​
speed
number
default:"1.0"
The speed of the generated speech, between 0.25 and 4.0. Values above 1.0 speed up the audio; values below slow it down.

​
Response

The response body is a binary audio stream with the Content-Type matching the requested response_format (e.g. audio/mpeg for MP3).
FormatContent-Type
mp3audio/mpeg
opusaudio/opus
aacaudio/aac
flacaudio/flac
wavaudio/wav
pcmaudio/pcm

​
Code examples

curl http://localhost:8787/v1/audio/speech \
  -H "Content-Type: application/json" \
  -H "x-portkey-provider: openai" \
  -H "x-portkey-api-key: $OPENAI_API_KEY" \
  -d '{
    "model": "tts-1",
    "input": "The Portkey AI Gateway routes requests to over 250 language models.",
    "voice": "alloy"
  }' \
  --output speech.mp3

Build docs developers (and LLMs) love

Get started for freeTalk to us