Skip to main content
POST
Text to Speech (Streaming)

Authorizations

Authorization
string
header
required

Specify the authorization token.

For more information, check out the Authorization Guide.

Body

application/json
text
string
required

The text to speak, in the voice's language.

Required string length: 1 - 5000
voiceId
string
required

The voice to use. List your voices with Get Voices.

modelId
string
default:nlpearl-v2-preview

The speech model.

nlpearl-v2-preview

pace
string
default:medium

How fast the voice speaks.

very_slow

slow

medium

fast

very_fast

tier
string
default:standard

Your place in the queue when the service is busy. priority goes ahead of waiting standard requests and is charged at the Priority rate only when it did.

standard

priority

outputFormat
string
default:mp3_44100_128

Codec, sample rate and bitrate of the audio, for example mp3_44100_128, pcm_16000 or ulaw_8000.

pcm_8000

pcm_16000

pcm_22050

pcm_24000

pcm_44100

pcm_48000

wav_8000

wav_16000

wav_22050

wav_24000

wav_44100

wav_48000

ulaw_8000

alaw_8000

mp3_22050_32

mp3_44100_32

mp3_44100_64

mp3_44100_96

mp3_44100_128

mp3_44100_192

opus_48000_32

opus_48000_64

opus_48000_96

opus_48000_128

opus_48000_192

Response

The audio, streamed as it is generated.

The response is of type file.