Text to Speech

POST

https://api.async.ai/text_to_speech

Generates speech using provided text and voice of your choice and returns audio.

Request Example

Shell

JavaScript

Java

Swift

curl --location --request POST 'https://api.async.ai/text_to_speech' \
--header 'x-api-key: <api-key>' \
--header 'version: v1' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model_id": "asyncflow_v2.0",
    "transcript": "Welcome to Async",
    "voice": {
        "mode": "id",
        "id": "e0f39dc4-f691-4e78-bba5-5c636692cc04"
    },
    "output_format": {
        "container": "raw",
        "encoding": "pcm_f32le",
        "sample_rate": 44100
    }
}'

Response Example

200 - Success

This endpoint returns a file in audio/mpeg format.

Request

Header Params

x-api-key

string

required

Example:

<api-key>

version

string

required

Example:

Body Params application/json

model_id

enum<string>

required

Model id

Allowed value:

asyncflow_v2.0

transcript

string

required

Text to convert to the speech

voice

object

required

Voice to use while make speech

mode

enum<string>

required

Allowed value:

string

required

Voice id

output_format

object

required

Output configurations

container

enum<string>

required

Output audio format

Allowed values:

rawmp3wav

encoding

enum<string>

optional

Output audio encoding. Ignore if mp3

Allowed values:

pcm_f32lepcm_s16le

sample_rate

integer

required

Output audio sample rate

>= 8000<= 48000

bit_rate

integer

optional

Output audio bit rate. Use only with mp3

>= 32000<= 320000

Default:

192000

string

required

Examples

Responses

🟢200Success

audio/mpeg

Body

object {0}

🟢200Success

🟠429TOO_MANY_CONCURRENT_REQUESTS

🟠429RATE_LIMIT_EXCEEDED

🟠429USAGE_LIMIT_EXCEEDED

🟠401INVALID_API_KEY

🟠404VOICE_NOT_FOUND

🟠404VERSION_NOT_FOUND

🟠400INVALID_LANGUAGE

🟠400FORMAT_NOT_RECOGNIZED

🔴500Server Error

Modified at 2025-07-15 14:04:33

Text to Speech (WebSocket)

Text to Speech with Word Timestamps