curl --request POST \
--url https://api.contextlm.ai/v1/generate_speech \
--header 'Content-Type: application/json' \
--header 'X-API-Key: <api-key>' \
--data @- <<EOF
{
"text": "Hello, how are you? [pause] I'm fine, thank you.",
"voice_id": "en-US-Phoenix-F-HD",
"model_id": "vivid",
"custom_prompt": "<string>",
"pitch": 0,
"speaking_rate": 1,
"output_format": "LINEAR16"
}
EOFimport requests
url = "https://api.contextlm.ai/v1/generate_speech"
payload = {
"text": "Hello, how are you? [pause] I'm fine, thank you.",
"voice_id": "en-US-Phoenix-F-HD",
"model_id": "vivid",
"custom_prompt": "<string>",
"pitch": 0,
"speaking_rate": 1,
"output_format": "LINEAR16"
}
headers = {
"X-API-Key": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'X-API-Key': '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({
text: 'Hello, how are you? [pause] I\'m fine, thank you.',
voice_id: 'en-US-Phoenix-F-HD',
model_id: 'vivid',
custom_prompt: '<string>',
pitch: 0,
speaking_rate: 1,
output_format: 'LINEAR16'
})
};
fetch('https://api.contextlm.ai/v1/generate_speech', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.contextlm.ai/v1/generate_speech",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'text' => 'Hello, how are you? [pause] I\'m fine, thank you.',
'voice_id' => 'en-US-Phoenix-F-HD',
'model_id' => 'vivid',
'custom_prompt' => '<string>',
'pitch' => 0,
'speaking_rate' => 1,
'output_format' => 'LINEAR16'
]),
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"X-API-Key: <api-key>"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.contextlm.ai/v1/generate_speech"
payload := strings.NewReader("{\n \"text\": \"Hello, how are you? [pause] I'm fine, thank you.\",\n \"voice_id\": \"en-US-Phoenix-F-HD\",\n \"model_id\": \"vivid\",\n \"custom_prompt\": \"<string>\",\n \"pitch\": 0,\n \"speaking_rate\": 1,\n \"output_format\": \"LINEAR16\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("X-API-Key", "<api-key>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.contextlm.ai/v1/generate_speech")
.header("X-API-Key", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"text\": \"Hello, how are you? [pause] I'm fine, thank you.\",\n \"voice_id\": \"en-US-Phoenix-F-HD\",\n \"model_id\": \"vivid\",\n \"custom_prompt\": \"<string>\",\n \"pitch\": 0,\n \"speaking_rate\": 1,\n \"output_format\": \"LINEAR16\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.contextlm.ai/v1/generate_speech")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["X-API-Key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"text\": \"Hello, how are you? [pause] I'm fine, thank you.\",\n \"voice_id\": \"en-US-Phoenix-F-HD\",\n \"model_id\": \"vivid\",\n \"custom_prompt\": \"<string>\",\n \"pitch\": 0,\n \"speaking_rate\": 1,\n \"output_format\": \"LINEAR16\"\n}"
response = http.request(request)
puts response.read_body{
"audiobytes": "<string>"
}{
"error": 123,
"detail": "<string>"
}{
"error": 123,
"detail": "<string>"
}{
"error": 123,
"detail": "<string>"
}{
"error": 123,
"detail": "<string>"
}{
"error": 123,
"detail": "<string>"
}Generate speech
Generates natural-sounding speech
curl --request POST \
--url https://api.contextlm.ai/v1/generate_speech \
--header 'Content-Type: application/json' \
--header 'X-API-Key: <api-key>' \
--data @- <<EOF
{
"text": "Hello, how are you? [pause] I'm fine, thank you.",
"voice_id": "en-US-Phoenix-F-HD",
"model_id": "vivid",
"custom_prompt": "<string>",
"pitch": 0,
"speaking_rate": 1,
"output_format": "LINEAR16"
}
EOFimport requests
url = "https://api.contextlm.ai/v1/generate_speech"
payload = {
"text": "Hello, how are you? [pause] I'm fine, thank you.",
"voice_id": "en-US-Phoenix-F-HD",
"model_id": "vivid",
"custom_prompt": "<string>",
"pitch": 0,
"speaking_rate": 1,
"output_format": "LINEAR16"
}
headers = {
"X-API-Key": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'X-API-Key': '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({
text: 'Hello, how are you? [pause] I\'m fine, thank you.',
voice_id: 'en-US-Phoenix-F-HD',
model_id: 'vivid',
custom_prompt: '<string>',
pitch: 0,
speaking_rate: 1,
output_format: 'LINEAR16'
})
};
fetch('https://api.contextlm.ai/v1/generate_speech', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.contextlm.ai/v1/generate_speech",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'text' => 'Hello, how are you? [pause] I\'m fine, thank you.',
'voice_id' => 'en-US-Phoenix-F-HD',
'model_id' => 'vivid',
'custom_prompt' => '<string>',
'pitch' => 0,
'speaking_rate' => 1,
'output_format' => 'LINEAR16'
]),
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"X-API-Key: <api-key>"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.contextlm.ai/v1/generate_speech"
payload := strings.NewReader("{\n \"text\": \"Hello, how are you? [pause] I'm fine, thank you.\",\n \"voice_id\": \"en-US-Phoenix-F-HD\",\n \"model_id\": \"vivid\",\n \"custom_prompt\": \"<string>\",\n \"pitch\": 0,\n \"speaking_rate\": 1,\n \"output_format\": \"LINEAR16\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("X-API-Key", "<api-key>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.contextlm.ai/v1/generate_speech")
.header("X-API-Key", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"text\": \"Hello, how are you? [pause] I'm fine, thank you.\",\n \"voice_id\": \"en-US-Phoenix-F-HD\",\n \"model_id\": \"vivid\",\n \"custom_prompt\": \"<string>\",\n \"pitch\": 0,\n \"speaking_rate\": 1,\n \"output_format\": \"LINEAR16\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.contextlm.ai/v1/generate_speech")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["X-API-Key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"text\": \"Hello, how are you? [pause] I'm fine, thank you.\",\n \"voice_id\": \"en-US-Phoenix-F-HD\",\n \"model_id\": \"vivid\",\n \"custom_prompt\": \"<string>\",\n \"pitch\": 0,\n \"speaking_rate\": 1,\n \"output_format\": \"LINEAR16\"\n}"
response = http.request(request)
puts response.read_body{
"audiobytes": "<string>"
}{
"error": 123,
"detail": "<string>"
}{
"error": 123,
"detail": "<string>"
}{
"error": 123,
"detail": "<string>"
}{
"error": 123,
"detail": "<string>"
}{
"error": 123,
"detail": "<string>"
}Authorizations
Body
Speech synthesis parameters
The text input to be converted to speech. Tags including [pause short], [pause] and [long pause] can be added to text to control the pause in speech. Only supported in vivid model.
"Hello, how are you? [pause] I'm fine, thank you."
The voice id to use in speech synthesis
"en-US-Phoenix-F-HD"
The model id to use in speech synthesis.
vivid, flow The custom prompt to use in speech synthesis. Only supported in vivid model.
Speaking pitch, in the range [-20.0, 20.0]. 20 means increase 20 semitones from the original pitch. -20 means decrease 20 semitones from the original pitch. Pitch is not fully supported in vivid model, mixed results may occur.
-20 <= x <= 20Speaking rate/speed, in the range [0.25, 4.0]. 1.0 is the normal native speed supported by the specific voice. 2.0 is twice as fast, and 0.5 is half as fast. Any other values < 0.25 or > 4.0 will return an error. Speaking rate is not fully supported in vivid model, mixed results may occur.
0.25 <= x <= 4The format of the audio byte stream. LINEAR16 a.k.a WAV is the best for audio quality.
LINEAR16, MP3, OGG_OPUS, MULAW Response
Successful response
