Hopp til hovedinnhold
POST
/
v1
/
audio
/
speech
Python (OpenAI SDK)
from openai import OpenAI

client = OpenAI(
    api_key="<COMETAPI_KEY>",
    base_url="https://api.cometapi.com/v1"
)

response = client.audio.speech.create(
    model="tts-1",
    voice="alloy",
    input="The quick brown fox jumped over the lazy dog."
)

response.stream_to_file("output.mp3")
"<string>"

Autorisasjoner

​
Authorization
string
header
påkrevd

Bearer token authentication. Use your CometAPI key.

Kropp

application/json
​
model
string
standard:tts-1
påkrevd

The TTS model to use. Choose a current speech model from the Models page.

​
input
string
påkrevd

The text to generate audio for. Maximum length is 4096 characters.

Maximum string length: 4096
​
voice
enum<string>
standard:alloy
påkrevd

The voice to use for speech synthesis.

Tilgjengelige alternativer:
alloy,
ash,
ballad,
coral,
echo,
fable,
onyx,
nova,
sage,
shimmer
​
response_format
enum<string>
standard:mp3

The audio output format.

Tilgjengelige alternativer:
mp3,
opus,
aac,
flac,
wav,
pcm
​
speed
number
standard:1

The speed of the generated audio. Select a value between 0.25 and 4.0.

Nødvendig område: 0.25 <= x <= 4

Svar

200 - audio/mpeg

The audio file content.

The response is of type file.