POST
/
v1
/
rest
/
speech
curl --request POST \
  --url https://tts.snr.audio/v1/rest/speech \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "input": "SNR Audio, helps you generate High Quality, Human-Like speech at one-tenth the cost",
  "voice": "rachel",
  "similarity": 0,
  "expressiveness": 0,
  "pitch": 1,
  "speed": 1
}'
"<any>"

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Query Parameters

​
codec
enum<string>
default:
mp3_44100_128
Available options:
mp3_44100_192,
mp3_44100_128,
mp3_44100_64,
mp3_44100_32,
mp3_44100_16,
mp3_22050_192,
mp3_22050_128,
pcm_16000,
pcm_22050,
pcm_24000,
pcm_44100,
mulaw_8000

Body

application/json
​
input
string
default:
SNR Audio, helps you generate High Quality, Human-Like speech at one-tenth the cost
required
​
voice
enum<string>
required
Available options:
rachel,
arnold,
clyde,
thomas,
lily,
sarah,
giovanni,
chris,
antoni,
glinda,
matilda
​
similarity
number
default:
0

Controls the similarity of generated speech to the specified voice. 0.0 means least similar, 1.0 means most similar.

​
expressiveness
number
default:
0

Controls the expressiveness of the generated speech. 0.0 means least expressive, 1.0 means most expressive.

Required range: 0 < x < 1
​
pitch
number
default:
1

Controls the pitch of the generated speech. 0.5 means half the original pitch, 1.0 means original pitch, 1.5 means 1.5 times the original pitch.

Required range: 0.5 < x < 1.5
​
speed
number
default:
1

Controls the speed of the generated speech. 0.5 means half the original speed, 1.0 means original speed, 2.0 means twice the original speed.

Required range: 0.5 < x < 2

Response

200
application/json
Successful Response

The response is of type any.

SNR Audio StreamingWebsockets