Text-to-speech

POST

/elevenlabs/text-to-speech/{voice_id}

From Elevenlabs Text-to-Speech
Official Documentation: https://elevenlabs.io/docs/api-reference/text-to-speech/convert

Currently Supported Models:
Models with 1x rate: eleven_multilingual_v2, eleven_flash_v2, eleven_multilingual_v1
Models with 0.5x rate: eleven_flash_v2_5, eleven_turbo_v2_5, eleven_turbo_v2

The actual rate is subject to the data returned by the models API, refer to the field character_cost_multiplier.

Price: 0.3 PTC / 1000 characters

Request

Path Params

voice_id

string

required

Example:

JBFqnCBsd6RMkjVDRZzb

Query Params

output_format

string

optional

可用列表
mp3_22050_32
mp3_44100_32
mp3_44100_64
mp3_44100_96
mp3_44100_128
mp3_44100_192
pcm_8000
pcm_16000
pcm_22050
pcm_24000
pcm_44100
pcm_48000
ulaw_8000
alaw_8000
opus_48000_32
opus_48000_64
opus_48000_96
opus_48000_128
opus_48000_192

Example:

mp3_44100_128

response_format

enum<string>

optional

默认url

Allowed values:

dataurl

Example:

url

Header Params

Authorization

string

optional

Example:

Bearer {{YOUR_API_KEY}}

Body Params application/json

text

string

required

model_id

string

optional

Example

{
  "text": "The first move is what sets everything in motion.",
  "model_id": "eleven_multilingual_v2"
}

Request samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://api.302.ai/elevenlabs/text-to-speech/JBFqnCBsd6RMkjVDRZzb?output_format=mp3_44100_128&response_format=url' \
--header 'Authorization: Bearer sk-jls4AaVBGoe1GwZD64qZA1qyKTN1MPHa4NmvH1cT68z7K1Zz' \
--header 'Content-Type: application/json' \
--data-raw '{
  "text": "The first move is what sets everything in motion.",
  "model_id": "eleven_multilingual_v2"
}'

Responses

🟢200成功

application/json

Body

object {0}

Example

{}

Modified at 2025-07-07 05:40:26

TTS-Flash-v2.5（Asynchronous result retrieval）

Speech-to-text