Text-to-Speech

POST

/google/v1/text-synthesize

From Google's TTS model, reference: https://cloud.google.com/text-to-speech#demo

Price: 40 PTC/million characters

Request

Query Params

response_format

string

optional

Required to be returned when uploading a blob.

Example:

url

Header Params

Authorization

string

optional

Example:

Bearer {{YOUR_API_KEY}}

Body Params application/json

audioConfig

object

required

audioEncoding

string

required

Value source: https://cloud.google.com/speech-to-text/docs/encoding?hl=en
Codec Name Lossless Usage Notes
MP3 MPEG Layer 3 Audio No MP3 encoding is a Beta feature, only available in v1p1beta1. For details, see the RecognitionConfig reference documentation.
FLAC Free Lossless Audio Codec Yes Stream requires 16-bit or 24-bit depth
LINEAR16 Linear PCM Yes 16-bit Linear Pulse Code Modulation (PCM) encoding. The file header must contain the sample rate.
MULAW μ-law No 8-bit PCM encoding
AMR Adaptive Multi-Rate Narrowband No Sample rate must be 8000 Hz
AMR_WB Adaptive Multi-Rate Wideband No Sample rate must be 16000 Hz
OGG_OPUS Opus encoded audio frames in Ogg container No Sample rate must be one of 8000 Hz, 12000 Hz, 16000 Hz, 24000 Hz, or 48000 Hz
SPEEX_WITH_HEADER_BYTE Speex Wideband No Sample rate must be 16000 Hz
WEBM_OPUS WebM Opus No Sample rate must be one of 8000 Hz, 12000 Hz, 16000 Hz, 24000 Hz, or 48000 Hz

effectsProfileId

array[string]

optional

Value source: https://cloud.google.com/text-to-speech/docs/audio-profiles?hl=en
wearable-class-device Smartwatches and other wearable devices, such as Apple Watch, Wear OS watches
handset-class-device Smartphones, such as Google Pixel, Samsung Galaxy, Apple iPhone
headphone-class-device Earbuds or headphones for audio playback, such as Sennheiser headphones
small-bluetooth-speaker-class-device Small home speakers, such as Google Home Mini
medium-bluetooth-speaker-class-device Smart home speakers, such as Google Home
large-home-entertainment-class-device Home entertainment systems or smart TVs, such as Google Home Max, LG TV
large-automotive-class-device Car speakers
telephony-class-application Interactive Voice Response (IVR) systems

pitch

number

optional

Optional. For input only. Speaking pitch, range [-20.0, 20.0]. 20 means increasing the pitch by 20 semitones above the original. -20 means decreasing the pitch by 20 semitones below the original.

speakingRate

number

optional

Optional. For input only. Speaking rate/speed, range [0.25, 2.0]. 1.0 represents the normal native speed supported by the specific voice. 2.0 represents twice the speed, 0.5 represents half the speed. If not set (0.0), it defaults to the native speed of 1.0. Any other value less than 0.25 or greater than 2.0 will return an error.

input

object

required

text

string

required

Input text to be converted

voice

object

required

Voice parameters reference: https://cloud.google.com/text-to-speech/docs/voices?hl=en

languageCode

string

required

Required. The language (and possibly region) of the voice, expressed as a BCP-47 language tag, e.g., "en-US". This parameter should not include a script tag (e.g., use "cmn-cn" instead of "cmn-Hant-cn"), as the script will be inferred from the input provided in SynthesisInput. The TTS service will use this parameter to help select an appropriate voice. Note that the TTS service may choose a voice with a slightly different language code than the one selected; it may substitute a different region (e.g., using en-US instead of en-CA if no Canadian voice is available), or even a different language, e.g., using "nb" (Norwegian Bokmål) instead of "no" (Norwegian).

name

string

required

Name of the voice. If neither name nor gender is set, the service will choose a voice based on other parameters (e.g., languageCode).

Example

{
    "audioConfig": {
        "audioEncoding": "LINEAR16",
        "effectsProfileId": [
            "headphone-class-device"
        ],
        "pitch": 0,
        "speakingRate": 0.96
    },
    "input": {
        "text": "302 is truly an awesome platform."
    },
    "voice": {
        "languageCode": "cmn-CN",
        "name": "cmn-CN-Chirp3-HD-Schedar"
    }
}

Request samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://api.302.ai/google/v1/text-synthesize?response_format=url' \
--header 'Authorization: Bearer sk-jls4AaVBGoe1GwZD64qZA1qyKTN1MPHa4NmvH1cT68z7K1Zz' \
--header 'Content-Type: application/json' \
--data-raw '{
    "audioConfig": {
        "audioEncoding": "LINEAR16",
        "effectsProfileId": [
            "headphone-class-device"
        ],
        "pitch": 0,
        "speakingRate": 0.96
    },
    "input": {
        "text": "302 is truly an awesome platform."
    },
    "voice": {
        "languageCode": "cmn-CN",
        "name": "cmn-CN-Chirp3-HD-Schedar"
    }
}'

Responses

🟢200成功

application/json

Body

audioConfig

object

required

audioEncoding

string

required

effectsProfileId

array[string]

required

pitch

integer

required

sampleRateHertz

integer

required

speakingRate

number

required

volumeGainDb

integer

required

audioContent

string

required

timepoints

array[string]

required

Example

{
    "audioConfig": {
        "audioEncoding": "LINEAR16",
        "effectsProfileId": [],
        "pitch": 0,
        "sampleRateHertz": 24000,
        "speakingRate": 0.96,
        "volumeGainDb": 0
    },
    "audioContent": "https://file.302.ai/gpt/imgs/20250617/671b1957ba22428abf0a1c9fb9f25241.mp3",
    "timepoints": []
}

Modified at 2025-06-18 06:53:33

Create text-to-speech request

gemini-2.5-flash-preview-tts