Gemini 2.5 Flash TTS Text-to-Speech
curl --request POST \
--url https://api.highwayapi.ai/v3/gemini-2.5-flash-tts \
--header 'Authorization: <authorization>' \
--header 'Content-Type: <content-type>' \
--data '
{
"contents": {
"role": "<string>",
"parts": {
"text": "<string>"
}
},
"generation_config": {
"temperature": 123,
"speech_config": {
"voice_config": {
"prebuilt_voice_config": {
"voice_name": "<string>"
}
},
"language_code": "<string>",
"multi_speaker_voice_config": {
"speaker_voice_configs": [
{
"speaker": "<string>",
"voice_config": {
"prebuilt_voice_config": {
"voice_name": "<string>"
}
}
}
]
}
}
}
}
'import requests
url = "https://api.highwayapi.ai/v3/gemini-2.5-flash-tts"
payload = {
"contents": {
"role": "<string>",
"parts": { "text": "<string>" }
},
"generation_config": {
"temperature": 123,
"speech_config": {
"voice_config": { "prebuilt_voice_config": { "voice_name": "<string>" } },
"language_code": "<string>",
"multi_speaker_voice_config": { "speaker_voice_configs": [
{
"speaker": "<string>",
"voice_config": { "prebuilt_voice_config": { "voice_name": "<string>" } }
}
] }
}
}
}
headers = {
"Content-Type": "<content-type>",
"Authorization": "<authorization>"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'Content-Type': '<content-type>', Authorization: '<authorization>'},
body: JSON.stringify({
contents: {role: '<string>', parts: {text: '<string>'}},
generation_config: {
temperature: 123,
speech_config: {
voice_config: {prebuilt_voice_config: {voice_name: '<string>'}},
language_code: '<string>',
multi_speaker_voice_config: {
speaker_voice_configs: [
{
speaker: '<string>',
voice_config: {prebuilt_voice_config: {voice_name: '<string>'}}
}
]
}
}
}
})
};
fetch('https://api.highwayapi.ai/v3/gemini-2.5-flash-tts', 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.highwayapi.ai/v3/gemini-2.5-flash-tts",
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([
'contents' => [
'role' => '<string>',
'parts' => [
'text' => '<string>'
]
],
'generation_config' => [
'temperature' => 123,
'speech_config' => [
'voice_config' => [
'prebuilt_voice_config' => [
'voice_name' => '<string>'
]
],
'language_code' => '<string>',
'multi_speaker_voice_config' => [
'speaker_voice_configs' => [
[
'speaker' => '<string>',
'voice_config' => [
'prebuilt_voice_config' => [
'voice_name' => '<string>'
]
]
]
]
]
]
]
]),
CURLOPT_HTTPHEADER => [
"Authorization: <authorization>",
"Content-Type: <content-type>"
],
]);
$response = curl_exec($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.highwayapi.ai/v3/gemini-2.5-flash-tts"
payload := strings.NewReader("{\n \"contents\": {\n \"role\": \"<string>\",\n \"parts\": {\n \"text\": \"<string>\"\n }\n },\n \"generation_config\": {\n \"temperature\": 123,\n \"speech_config\": {\n \"voice_config\": {\n \"prebuilt_voice_config\": {\n \"voice_name\": \"<string>\"\n }\n },\n \"language_code\": \"<string>\",\n \"multi_speaker_voice_config\": {\n \"speaker_voice_configs\": [\n {\n \"speaker\": \"<string>\",\n \"voice_config\": {\n \"prebuilt_voice_config\": {\n \"voice_name\": \"<string>\"\n }\n }\n }\n ]\n }\n }\n }\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Content-Type", "<content-type>")
req.Header.Add("Authorization", "<authorization>")
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.highwayapi.ai/v3/gemini-2.5-flash-tts")
.header("Content-Type", "<content-type>")
.header("Authorization", "<authorization>")
.body("{\n \"contents\": {\n \"role\": \"<string>\",\n \"parts\": {\n \"text\": \"<string>\"\n }\n },\n \"generation_config\": {\n \"temperature\": 123,\n \"speech_config\": {\n \"voice_config\": {\n \"prebuilt_voice_config\": {\n \"voice_name\": \"<string>\"\n }\n },\n \"language_code\": \"<string>\",\n \"multi_speaker_voice_config\": {\n \"speaker_voice_configs\": [\n {\n \"speaker\": \"<string>\",\n \"voice_config\": {\n \"prebuilt_voice_config\": {\n \"voice_name\": \"<string>\"\n }\n }\n }\n ]\n }\n }\n }\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.highwayapi.ai/v3/gemini-2.5-flash-tts")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Content-Type"] = '<content-type>'
request["Authorization"] = '<authorization>'
request.body = "{\n \"contents\": {\n \"role\": \"<string>\",\n \"parts\": {\n \"text\": \"<string>\"\n }\n },\n \"generation_config\": {\n \"temperature\": 123,\n \"speech_config\": {\n \"voice_config\": {\n \"prebuilt_voice_config\": {\n \"voice_name\": \"<string>\"\n }\n },\n \"language_code\": \"<string>\",\n \"multi_speaker_voice_config\": {\n \"speaker_voice_configs\": [\n {\n \"speaker\": \"<string>\",\n \"voice_config\": {\n \"prebuilt_voice_config\": {\n \"voice_name\": \"<string>\"\n }\n }\n }\n ]\n }\n }\n }\n}"
response = http.request(request)
puts response.read_body{
"audioContent": "<string>",
"usageMetadata": {
"totalTokenCount": 123,
"promptTokenCount": 123,
"candidatesTokenCount": 123
}
}Audio
Gemini 2.5 Flash TTS Text-to-Speech
POST
/
v3
/
gemini-2.5-flash-tts
Gemini 2.5 Flash TTS Text-to-Speech
curl --request POST \
--url https://api.highwayapi.ai/v3/gemini-2.5-flash-tts \
--header 'Authorization: <authorization>' \
--header 'Content-Type: <content-type>' \
--data '
{
"contents": {
"role": "<string>",
"parts": {
"text": "<string>"
}
},
"generation_config": {
"temperature": 123,
"speech_config": {
"voice_config": {
"prebuilt_voice_config": {
"voice_name": "<string>"
}
},
"language_code": "<string>",
"multi_speaker_voice_config": {
"speaker_voice_configs": [
{
"speaker": "<string>",
"voice_config": {
"prebuilt_voice_config": {
"voice_name": "<string>"
}
}
}
]
}
}
}
}
'import requests
url = "https://api.highwayapi.ai/v3/gemini-2.5-flash-tts"
payload = {
"contents": {
"role": "<string>",
"parts": { "text": "<string>" }
},
"generation_config": {
"temperature": 123,
"speech_config": {
"voice_config": { "prebuilt_voice_config": { "voice_name": "<string>" } },
"language_code": "<string>",
"multi_speaker_voice_config": { "speaker_voice_configs": [
{
"speaker": "<string>",
"voice_config": { "prebuilt_voice_config": { "voice_name": "<string>" } }
}
] }
}
}
}
headers = {
"Content-Type": "<content-type>",
"Authorization": "<authorization>"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'Content-Type': '<content-type>', Authorization: '<authorization>'},
body: JSON.stringify({
contents: {role: '<string>', parts: {text: '<string>'}},
generation_config: {
temperature: 123,
speech_config: {
voice_config: {prebuilt_voice_config: {voice_name: '<string>'}},
language_code: '<string>',
multi_speaker_voice_config: {
speaker_voice_configs: [
{
speaker: '<string>',
voice_config: {prebuilt_voice_config: {voice_name: '<string>'}}
}
]
}
}
}
})
};
fetch('https://api.highwayapi.ai/v3/gemini-2.5-flash-tts', 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.highwayapi.ai/v3/gemini-2.5-flash-tts",
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([
'contents' => [
'role' => '<string>',
'parts' => [
'text' => '<string>'
]
],
'generation_config' => [
'temperature' => 123,
'speech_config' => [
'voice_config' => [
'prebuilt_voice_config' => [
'voice_name' => '<string>'
]
],
'language_code' => '<string>',
'multi_speaker_voice_config' => [
'speaker_voice_configs' => [
[
'speaker' => '<string>',
'voice_config' => [
'prebuilt_voice_config' => [
'voice_name' => '<string>'
]
]
]
]
]
]
]
]),
CURLOPT_HTTPHEADER => [
"Authorization: <authorization>",
"Content-Type: <content-type>"
],
]);
$response = curl_exec($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.highwayapi.ai/v3/gemini-2.5-flash-tts"
payload := strings.NewReader("{\n \"contents\": {\n \"role\": \"<string>\",\n \"parts\": {\n \"text\": \"<string>\"\n }\n },\n \"generation_config\": {\n \"temperature\": 123,\n \"speech_config\": {\n \"voice_config\": {\n \"prebuilt_voice_config\": {\n \"voice_name\": \"<string>\"\n }\n },\n \"language_code\": \"<string>\",\n \"multi_speaker_voice_config\": {\n \"speaker_voice_configs\": [\n {\n \"speaker\": \"<string>\",\n \"voice_config\": {\n \"prebuilt_voice_config\": {\n \"voice_name\": \"<string>\"\n }\n }\n }\n ]\n }\n }\n }\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Content-Type", "<content-type>")
req.Header.Add("Authorization", "<authorization>")
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.highwayapi.ai/v3/gemini-2.5-flash-tts")
.header("Content-Type", "<content-type>")
.header("Authorization", "<authorization>")
.body("{\n \"contents\": {\n \"role\": \"<string>\",\n \"parts\": {\n \"text\": \"<string>\"\n }\n },\n \"generation_config\": {\n \"temperature\": 123,\n \"speech_config\": {\n \"voice_config\": {\n \"prebuilt_voice_config\": {\n \"voice_name\": \"<string>\"\n }\n },\n \"language_code\": \"<string>\",\n \"multi_speaker_voice_config\": {\n \"speaker_voice_configs\": [\n {\n \"speaker\": \"<string>\",\n \"voice_config\": {\n \"prebuilt_voice_config\": {\n \"voice_name\": \"<string>\"\n }\n }\n }\n ]\n }\n }\n }\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.highwayapi.ai/v3/gemini-2.5-flash-tts")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Content-Type"] = '<content-type>'
request["Authorization"] = '<authorization>'
request.body = "{\n \"contents\": {\n \"role\": \"<string>\",\n \"parts\": {\n \"text\": \"<string>\"\n }\n },\n \"generation_config\": {\n \"temperature\": 123,\n \"speech_config\": {\n \"voice_config\": {\n \"prebuilt_voice_config\": {\n \"voice_name\": \"<string>\"\n }\n },\n \"language_code\": \"<string>\",\n \"multi_speaker_voice_config\": {\n \"speaker_voice_configs\": [\n {\n \"speaker\": \"<string>\",\n \"voice_config\": {\n \"prebuilt_voice_config\": {\n \"voice_name\": \"<string>\"\n }\n }\n }\n ]\n }\n }\n }\n}"
response = http.request(request)
puts response.read_body{
"audioContent": "<string>",
"usageMetadata": {
"totalTokenCount": 123,
"promptTokenCount": 123,
"candidatesTokenCount": 123
}
}Convert text to speech based on the Vertex AI generateContent API. The request body format is fully consistent with the official Vertex AI API. Both synchronous (single request, single response) and streaming (single request, streaming response) modes are supported. The output is in LINEAR16 PCM format (24kHz, mono, 16-bit signed little-endian) and does not include a WAV header.
Request Headers
string
required
Enum value:
application/jsonstring
required
Bearer authentication format: Bearer {{API Key}}.
Request Body
object
required
Hide properties
Hide properties
string
default:"user"
required
Role, fixed as userAllowed value:
userobject
required
Hide properties
Hide properties
string
required
The text content to synthesize into speech. The Vertex AI API combines the prompt and text into a single field in the format ’: ’, for example ‘Say the following in a curious way: OK, so… tell me about this AI thing.’. The total size can be up to 8000 bytes, and audio exceeding 655 seconds will be truncated. Inline marker tags are supported: [sigh], [laughing], [uhm], [sarcasm], [robotic], [shouting], [whispering], [extremely fast], [short pause], [medium pause], [long pause]Length limit: 0 - 8000
object
required
Hide properties
Hide properties
number
default:2
Temperature parameter, controlling the randomness and creativity of speech generation. Higher values produce more creative and diverse results, while lower values are more predictable and focused. Valid range: (0.0, 2.0], recommended value: 2.0Value range: [0, 2]
object
required
Hide properties
Hide properties
object
Single-speaker voice configuration. Choose either this or multi_speaker_voice_config
Hide properties
Hide properties
object
Hide properties
Hide properties
string
Prebuilt voice name (case-insensitive). 30 available voices (both male and female voices are available)Allowed values:
Achernar, Achird, Algenib, Algieba, Alnilam, Aoede, Autonoe, Callirrhoe, Charon, Despina, Enceladus, Erinome, Fenrir, Gacrux, Iapetus, Kore, Laomedeia, Leda, Orus, Pulcherrima, Puck, Rasalgethi, Sadachbia, Sadaltager, Schedar, Sulafat, Umbriel, Vindemiatrix, Zephyr, Zubenelgenubistring
required
Language code (BCP-47 format, case-insensitive). GA languages: ar-EG, bn-BD, nl-NL, en-IN, en-US, fr-FR, de-DE, hi-IN, id-ID, it-IT, ja-JP, ko-KR, mr-IN, pl-PL, pt-BR, ro-RO, ru-RU, es-ES, ta-IN, te-IN, th-TH, tr-TR, uk-UA, vi-VN. Preview languages include cmn-CN (Mandarin Chinese) and 63 othersAllowed values:
af-ZA, am-ET, ar-001, ar-EG, az-AZ, be-BY, bg-BG, bn-BD, ca-ES, ceb-PH, cmn-CN, cmn-TW, cs-CZ, da-DK, de-DE, el-GR, en-AU, en-GB, en-IN, en-US, es-419, es-ES, es-MX, et-EE, eu-ES, fa-IR, fi-FI, fil-PH, fr-CA, fr-FR, gl-ES, gu-IN, he-IL, hi-IN, hr-HR, ht-HT, hu-HU, hy-AM, id-ID, is-IS, it-IT, ja-JP, jv-JV, ka-GE, kn-IN, ko-KR, kok-IN, la-VA, lb-LU, lo-LA, lt-LT, lv-LV, mai-IN, mg-MG, mk-MK, ml-IN, mn-MN, mr-IN, ms-MY, my-MM, nb-NO, ne-NP, nl-NL, nn-NO, or-IN, pa-IN, pl-PL, ps-AF, pt-BR, pt-PT, ro-RO, ru-RU, sd-IN, si-LK, sk-SK, sl-SI, sq-AL, sr-RS, sv-SE, sw-KE, ta-IN, te-IN, th-TH, tr-TR, uk-UA, ur-PK, vi-VNobject
Multi-speaker voice configuration. Choose either this or voice_config. Note: gemini-2.5-flash-lite-preview-tts does not support multi-speaker synthesis
Hide properties
Hide properties
object[]
List of speaker voice configurations
Hide properties
Hide properties
string
required
Speaker alias, which must consist only of alphanumeric characters and contain no spaces. It must match the speaker identifier in contents.parts.text
object
required
Hide properties
Hide properties
object
Hide properties
Hide properties
string
Prebuilt voice name (case-insensitive). 30 available voices (both male and female voices are available)Allowed values:
Achernar, Achird, Algenib, Algieba, Alnilam, Aoede, Autonoe, Callirrhoe, Charon, Despina, Enceladus, Erinome, Fenrir, Gacrux, Iapetus, Kore, Laomedeia, Leda, Orus, Pulcherrima, Puck, Rasalgethi, Sadachbia, Sadaltager, Schedar, Sulafat, Umbriel, Vindemiatrix, Zephyr, ZubenelgenubiResponse Information
string
Base64-encoded audio content. The format is LINEAR16 PCM (24kHz, mono, 16-bit signed little-endian) and does not include a WAV header. The client can use ffmpeg to convert it: ffmpeg -f s16le -ar 24k -ac 1 -i input.raw output.wav
⌘I