Skip to main content
POST /v1/audio/speech
Generates audio from text input using text-to-speech models.

​
Request Body

​
model
string
required
The TTS model to use. Options include tts-1 and tts-1-hd.
​
input
string
required
The text to generate audio for. Maximum length is 4096 characters.
​
voice
string
required
The voice to use. Supported voices: alloy, echo, fable, onyx, nova, shimmer.
​
response_format
string
default:"mp3"
The audio format. Supported formats: mp3, opus, aac, flac, wav, pcm.
​
speed
number
default:"1.0"
The speed of the generated audio. Range: 0.25 to 4.0.

​
Response

Returns the audio file content in the requested format. The response has the appropriate Content-Type header based on the format.

​
Examples

​
Basic Text-to-Speech

from openai import OpenAI

client = OpenAI(
    api_key="sk-voidai-your_key_here",
    base_url="https://api.voidai.app/v1"
)

response = client.audio.speech.create(
    model="tts-1",
    voice="alloy",
    input="Hello! This is a test of the text-to-speech API."
)

response.stream_to_file("output.mp3")

​
High-Definition Audio

response = client.audio.speech.create(
    model="tts-1-hd",
    voice="nova",
    input="Welcome to VoidAI! Experience the power of unified AI APIs.",
    response_format="flac"
)

response.stream_to_file("output.flac")

​
Adjusting Speed

# Slower speech (0.5x speed)
response = client.audio.speech.create(
    model="tts-1",
    voice="onyx",
    input="This is spoken more slowly for clarity.",
    speed=0.5
)

# Faster speech (1.5x speed)
response = client.audio.speech.create(
    model="tts-1",
    voice="onyx",
    input="This is spoken more quickly.",
    speed=1.5
)

​
Voice Descriptions

VoiceDescription
alloyNeutral, balanced voice
echoWarm, conversational voice
fableExpressive, narrative voice
onyxDeep, authoritative voice
novaFriendly, energetic voice
shimmerClear, refined voice

​
Audio Format Comparison

FormatQualityFile SizeUse Case
mp3GoodSmallGeneral use, web streaming
opusExcellentSmallReal-time streaming
aacGoodSmallMobile apps
flacLosslessLargeArchival, high quality
wavLosslessLargeProfessional editing
pcmRawLargeAudio processing
Use tts-1 for lower latency and tts-1-hd for higher quality audio generation.