Text-to-Speech (SSE)

curl --request POST \
  --url https://api.cartesia.ai/tts/sse \
  --header 'Authorization: Bearer <token>' \
  --header 'Cartesia-Version: <cartesia-version>' \
  --header 'Content-Type: application/json' \
  --data @- <<EOF
{
  "model_id": "sonic-3.6",
  "transcript": "Hi there, it's awesome to meet you.",
  "voice": "db6b0ed5-d5d3-463d-ae85-518a07d3c2b4",
  "output_format": {
    "container": "raw"
  },
  "language": "<string>",
  "locale": "<string>",
  "accent": "<string>",
  "normalization": "auto",
  "add_timestamps": false,
  "add_phoneme_timestamps": false,
  "use_normalized_timestamps": true,
  "pronunciation_dict_id": "<string>",
  "generation_config": {
    "volume": 1,
    "speed": 1
  },
  "context_id": "<string>"
}
EOF

import requests

url = "https://api.cartesia.ai/tts/sse"

payload = {
    "model_id": "sonic-3.6",
    "transcript": "Hi there, it's awesome to meet you.",
    "voice": "db6b0ed5-d5d3-463d-ae85-518a07d3c2b4",
    "output_format": { "container": "raw" },
    "language": "<string>",
    "locale": "<string>",
    "accent": "<string>",
    "normalization": "auto",
    "add_timestamps": False,
    "add_phoneme_timestamps": False,
    "use_normalized_timestamps": True,
    "pronunciation_dict_id": "<string>",
    "generation_config": {
        "volume": 1,
        "speed": 1
    },
    "context_id": "<string>"
}
headers = {
    "Cartesia-Version": "<cartesia-version>",
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {
    'Cartesia-Version': '<cartesia-version>',
    Authorization: 'Bearer <token>',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model_id: 'sonic-3.6',
    transcript: 'Hi there, it\'s awesome to meet you.',
    voice: 'db6b0ed5-d5d3-463d-ae85-518a07d3c2b4',
    output_format: {container: 'raw'},
    language: '<string>',
    locale: '<string>',
    accent: '<string>',
    normalization: 'auto',
    add_timestamps: false,
    add_phoneme_timestamps: false,
    use_normalized_timestamps: true,
    pronunciation_dict_id: '<string>',
    generation_config: {volume: 1, speed: 1},
    context_id: '<string>'
  })
};

fetch('https://api.cartesia.ai/tts/sse', 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.cartesia.ai/tts/sse",
  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([
    'model_id' => 'sonic-3.6',
    'transcript' => 'Hi there, it\'s awesome to meet you.',
    'voice' => 'db6b0ed5-d5d3-463d-ae85-518a07d3c2b4',
    'output_format' => [
        'container' => 'raw'
    ],
    'language' => '<string>',
    'locale' => '<string>',
    'accent' => '<string>',
    'normalization' => 'auto',
    'add_timestamps' => false,
    'add_phoneme_timestamps' => false,
    'use_normalized_timestamps' => true,
    'pronunciation_dict_id' => '<string>',
    'generation_config' => [
        'volume' => 1,
        'speed' => 1
    ],
    'context_id' => '<string>'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Cartesia-Version: <cartesia-version>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($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.cartesia.ai/tts/sse"

	payload := strings.NewReader("{\n  \"model_id\": \"sonic-3.6\",\n  \"transcript\": \"Hi there, it's awesome to meet you.\",\n  \"voice\": \"db6b0ed5-d5d3-463d-ae85-518a07d3c2b4\",\n  \"output_format\": {\n    \"container\": \"raw\"\n  },\n  \"language\": \"<string>\",\n  \"locale\": \"<string>\",\n  \"accent\": \"<string>\",\n  \"normalization\": \"auto\",\n  \"add_timestamps\": false,\n  \"add_phoneme_timestamps\": false,\n  \"use_normalized_timestamps\": true,\n  \"pronunciation_dict_id\": \"<string>\",\n  \"generation_config\": {\n    \"volume\": 1,\n    \"speed\": 1\n  },\n  \"context_id\": \"<string>\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Cartesia-Version", "<cartesia-version>")
	req.Header.Add("Authorization", "Bearer <token>")
	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.cartesia.ai/tts/sse")
  .header("Cartesia-Version", "<cartesia-version>")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model_id\": \"sonic-3.6\",\n  \"transcript\": \"Hi there, it's awesome to meet you.\",\n  \"voice\": \"db6b0ed5-d5d3-463d-ae85-518a07d3c2b4\",\n  \"output_format\": {\n    \"container\": \"raw\"\n  },\n  \"language\": \"<string>\",\n  \"locale\": \"<string>\",\n  \"accent\": \"<string>\",\n  \"normalization\": \"auto\",\n  \"add_timestamps\": false,\n  \"add_phoneme_timestamps\": false,\n  \"use_normalized_timestamps\": true,\n  \"pronunciation_dict_id\": \"<string>\",\n  \"generation_config\": {\n    \"volume\": 1,\n    \"speed\": 1\n  },\n  \"context_id\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.cartesia.ai/tts/sse")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Cartesia-Version"] = '<cartesia-version>'
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model_id\": \"sonic-3.6\",\n  \"transcript\": \"Hi there, it's awesome to meet you.\",\n  \"voice\": \"db6b0ed5-d5d3-463d-ae85-518a07d3c2b4\",\n  \"output_format\": {\n    \"container\": \"raw\"\n  },\n  \"language\": \"<string>\",\n  \"locale\": \"<string>\",\n  \"accent\": \"<string>\",\n  \"normalization\": \"auto\",\n  \"add_timestamps\": false,\n  \"add_phoneme_timestamps\": false,\n  \"use_normalized_timestamps\": true,\n  \"pronunciation_dict_id\": \"<string>\",\n  \"generation_config\": {\n    \"volume\": 1,\n    \"speed\": 1\n  },\n  \"context_id\": \"<string>\"\n}"

response = http.request(request)
puts response.read_body

{
  "type": "chunk",
  "done": false,
  "status_code": 206,
  "step_time": 123,
  "context_id": "50dc3b5e-5841-4aa1-9f94-60cfb9aead79",
  "data": "aSDinaTvuI8gbWludGxpZnk="
}

POST

tts

sse

Text-to-Speech (SSE)

curl --request POST \
  --url https://api.cartesia.ai/tts/sse \
  --header 'Authorization: Bearer <token>' \
  --header 'Cartesia-Version: <cartesia-version>' \
  --header 'Content-Type: application/json' \
  --data @- <<EOF
{
  "model_id": "sonic-3.6",
  "transcript": "Hi there, it's awesome to meet you.",
  "voice": "db6b0ed5-d5d3-463d-ae85-518a07d3c2b4",
  "output_format": {
    "container": "raw"
  },
  "language": "<string>",
  "locale": "<string>",
  "accent": "<string>",
  "normalization": "auto",
  "add_timestamps": false,
  "add_phoneme_timestamps": false,
  "use_normalized_timestamps": true,
  "pronunciation_dict_id": "<string>",
  "generation_config": {
    "volume": 1,
    "speed": 1
  },
  "context_id": "<string>"
}
EOF

import requests

url = "https://api.cartesia.ai/tts/sse"

payload = {
    "model_id": "sonic-3.6",
    "transcript": "Hi there, it's awesome to meet you.",
    "voice": "db6b0ed5-d5d3-463d-ae85-518a07d3c2b4",
    "output_format": { "container": "raw" },
    "language": "<string>",
    "locale": "<string>",
    "accent": "<string>",
    "normalization": "auto",
    "add_timestamps": False,
    "add_phoneme_timestamps": False,
    "use_normalized_timestamps": True,
    "pronunciation_dict_id": "<string>",
    "generation_config": {
        "volume": 1,
        "speed": 1
    },
    "context_id": "<string>"
}
headers = {
    "Cartesia-Version": "<cartesia-version>",
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {
    'Cartesia-Version': '<cartesia-version>',
    Authorization: 'Bearer <token>',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model_id: 'sonic-3.6',
    transcript: 'Hi there, it\'s awesome to meet you.',
    voice: 'db6b0ed5-d5d3-463d-ae85-518a07d3c2b4',
    output_format: {container: 'raw'},
    language: '<string>',
    locale: '<string>',
    accent: '<string>',
    normalization: 'auto',
    add_timestamps: false,
    add_phoneme_timestamps: false,
    use_normalized_timestamps: true,
    pronunciation_dict_id: '<string>',
    generation_config: {volume: 1, speed: 1},
    context_id: '<string>'
  })
};

fetch('https://api.cartesia.ai/tts/sse', 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.cartesia.ai/tts/sse",
  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([
    'model_id' => 'sonic-3.6',
    'transcript' => 'Hi there, it\'s awesome to meet you.',
    'voice' => 'db6b0ed5-d5d3-463d-ae85-518a07d3c2b4',
    'output_format' => [
        'container' => 'raw'
    ],
    'language' => '<string>',
    'locale' => '<string>',
    'accent' => '<string>',
    'normalization' => 'auto',
    'add_timestamps' => false,
    'add_phoneme_timestamps' => false,
    'use_normalized_timestamps' => true,
    'pronunciation_dict_id' => '<string>',
    'generation_config' => [
        'volume' => 1,
        'speed' => 1
    ],
    'context_id' => '<string>'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Cartesia-Version: <cartesia-version>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($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.cartesia.ai/tts/sse"

	payload := strings.NewReader("{\n  \"model_id\": \"sonic-3.6\",\n  \"transcript\": \"Hi there, it's awesome to meet you.\",\n  \"voice\": \"db6b0ed5-d5d3-463d-ae85-518a07d3c2b4\",\n  \"output_format\": {\n    \"container\": \"raw\"\n  },\n  \"language\": \"<string>\",\n  \"locale\": \"<string>\",\n  \"accent\": \"<string>\",\n  \"normalization\": \"auto\",\n  \"add_timestamps\": false,\n  \"add_phoneme_timestamps\": false,\n  \"use_normalized_timestamps\": true,\n  \"pronunciation_dict_id\": \"<string>\",\n  \"generation_config\": {\n    \"volume\": 1,\n    \"speed\": 1\n  },\n  \"context_id\": \"<string>\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Cartesia-Version", "<cartesia-version>")
	req.Header.Add("Authorization", "Bearer <token>")
	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.cartesia.ai/tts/sse")
  .header("Cartesia-Version", "<cartesia-version>")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model_id\": \"sonic-3.6\",\n  \"transcript\": \"Hi there, it's awesome to meet you.\",\n  \"voice\": \"db6b0ed5-d5d3-463d-ae85-518a07d3c2b4\",\n  \"output_format\": {\n    \"container\": \"raw\"\n  },\n  \"language\": \"<string>\",\n  \"locale\": \"<string>\",\n  \"accent\": \"<string>\",\n  \"normalization\": \"auto\",\n  \"add_timestamps\": false,\n  \"add_phoneme_timestamps\": false,\n  \"use_normalized_timestamps\": true,\n  \"pronunciation_dict_id\": \"<string>\",\n  \"generation_config\": {\n    \"volume\": 1,\n    \"speed\": 1\n  },\n  \"context_id\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.cartesia.ai/tts/sse")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Cartesia-Version"] = '<cartesia-version>'
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model_id\": \"sonic-3.6\",\n  \"transcript\": \"Hi there, it's awesome to meet you.\",\n  \"voice\": \"db6b0ed5-d5d3-463d-ae85-518a07d3c2b4\",\n  \"output_format\": {\n    \"container\": \"raw\"\n  },\n  \"language\": \"<string>\",\n  \"locale\": \"<string>\",\n  \"accent\": \"<string>\",\n  \"normalization\": \"auto\",\n  \"add_timestamps\": false,\n  \"add_phoneme_timestamps\": false,\n  \"use_normalized_timestamps\": true,\n  \"pronunciation_dict_id\": \"<string>\",\n  \"generation_config\": {\n    \"volume\": 1,\n    \"speed\": 1\n  },\n  \"context_id\": \"<string>\"\n}"

response = http.request(request)
puts response.read_body

{
  "type": "chunk",
  "done": false,
  "status_code": 206,
  "step_time": 123,
  "context_id": "50dc3b5e-5841-4aa1-9f94-60cfb9aead79",
  "data": "aSDinaTvuI8gbWludGxpZnk="
}

Authorizations

Authorization

string

header

default:$CARTESIA_API_KEY

required

Cartesia API key (sk_car_...). Get one at play.cartesia.ai/keys.

Headers

Cartesia-Version

enum<string>

default:2026-08-14

required

API version header.

Available options:

2026-08-14

Example:

"2026-08-14"

Body

application/json

model_id

enum<string>

default:sonic-3.6

required

The ID of the model to use for the generation. See Models all options.

Available options:

sonic-3.6,

sonic-3.5,

sonic-3,

sonic-latest

Example:

"sonic-3.6"

transcript

string

default:Hi there, it's awesome to meet you.

required

voice

required

The ID of the voice.

Example:

"db6b0ed5-d5d3-463d-ae85-518a07d3c2b4"

output_format

SSEOutputFormat · object

required

Show child attributes

language

string | null

The transcript's language or locale (for example en or en-GB). language and locale accept the same values. Set one or the other, never both; setting both returns a 400 error. See supported codes.

locale

string | null

The transcript's language or locale (for example en or en-GB). locale and language accept the same values. Set one or the other, never both; setting both returns a 400 error. See supported codes.

accent

string | null

Usually unnecessary: Cartesia picks the closest accent the voice supports for the requested language or locale. Set it only to make a multilingual voice sound accented (e.g. speak English with a French accent). Must come from the voice's Get Voice accents field. Learn more here.

normalization

string | null

default:auto

Text normalization. auto (default) runs the locale-aware normalizer, off skips it, or pass a language or locale code (for example en or en-IN) to pin the normalizer independently of the generation language. See Text Normalization.

add_timestamps

boolean | null

default:false

Whether to return word-level timestamps. If false (default), no word timestamps will be produced at all. If true, the server will return timestamp events containing word-level timing information.

add_phoneme_timestamps

boolean | null

default:false

Whether to return phoneme-level timestamps. If false (default), no phoneme timestamps will be produced. If true, the server will return timestamp events containing phoneme-level timing information.

use_normalized_timestamps

boolean | null

Whether to use normalized timestamps (True) or original timestamps (False).

pronunciation_dict_id

string | null

The ID of a pronunciation dictionary to use for the generation. Pronunciation dictionaries are supported by sonic-3 models and newer.

generation_config

GenerationConfig · object

Configure the various attributes of the generated speech. Available on sonic-3 and newer models; not available on earlier models.

See Volume, Speed, and Emotion for a guide on this option.

Show child attributes

context_id

string | null

This can be any string value you find useful. The server will echo back the same context_id in events that it sends.

Contexts on the TTS (WebSocket) endpoint are used for continuations. > The TTS (SSE) endpoint does not support continuations, so most users just ignore this property.

Response

200 - text/event-stream

Server-sent events stream. Each frame is data: <json>\n\n where the JSON payload matches TTSSSEEvent.

TTSSSEChunkEvent
TTSSSETimestampsEvent
TTSSSEPhonemeTimestampsEvent
TTSSSEDoneEvent
TTSSSEErrorEvent

Audio data chunk.

type

enum<string>

required

Event type identifier.

Available options:

chunk

done

enum<boolean>

required

Whether this is the final event for the request. Always false for chunk events.

Available options:

false

data

string

required

Base64-encoded audio data.

step_time

number

required

Server-side processing time for this chunk in milliseconds.

status_code

integer

required

HTTP-style status code.

context_id

string | null

The context ID echoed back from the request, if one was provided.

Use the API

API Status

Models

TTS

STT

Watermarking

Managed Agents

Auth

Voices

Pronunciation Dicts

Datasets

Files

Fine Tunes

Infill

Admin

Text-to-Speech (SSE)

Authorizations

Headers

Body

Response