Text to Speech

Convert text to natural-sounding speech

POST /tts-synthesize

cURL

curl -X POST https://api.60db.ai/tts-synthesize \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Hello, world! This is a test of the text to speech API.",
    "voice_id": "default-voice",
    "enhance": true,
    "speed": 1.0
  }'

import { SixtyDBClient } from "60db";

const client = new SixtyDBClient("your-api-key");

const audio = await client.textToSpeech({
  text: "Hello, world! This is a test of the text to speech API.",
  voice_id: "default-voice",
  enhance: true,
  speed: 1.0,
});

// audio is an ArrayBuffer

from sixtydb import SixtyDBClient

client = SixtyDBClient('your-api-key')

audio = client.text_to_speech(
    text='Hello, world! This is a test of the text to speech API.',
    voice_id='default-voice',
    enhance=True,
    speed=1.0
)

# Save to file
with open('output.mp3', 'wb') as f:
    f.write(audio)

Response

{
  "success": true,
  "message": "Audio generated successfully",
  "audio_base64": "SUQzBAAAAAAAI1RTU0UAAAAPAAADTGF2ZjU4Ljc2LjEwMAAAAAAAAAAAAAAA...",
  "sample_rate": 24000,
  "duration_seconds": 3.5,
  "encoding": "mp3",
  "output_format": "mp3"
}

Request

Headers

Authorization · string · required

Bearer token with your API key

Content-Type · string · required

application/json

Body

text · string · required

The text to convert to speech (max 5000 characters)

voice_id · string

ID of the voice to use (default: system default voice)

voice · string

Alternative way to specify voice name

enhance · boolean · default: "true"

Enable audio enhancement for better quality

speed · number · default: "1.0"

Speech speed multiplier (0.5 to 2.0)

pitch · number · default: "1.0"

Voice pitch multiplier (0.5 to 2.0)

output_format · string · default: "mp3"

Audio output format: mp3, wav, ogg, flac

Response

success · boolean

Indicates if the request was successful

message · string

Status message

audio_base64 · string

Base64-encoded audio data

sample_rate · number

Audio sample rate in Hz

duration_seconds · number

Duration of the audio in seconds

encoding · string

Audio encoding format

output_format · string

Audio output format

cURL

curl -X POST https://api.60db.ai/tts-synthesize \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Hello, world! This is a test of the text to speech API.",
    "voice_id": "default-voice",
    "enhance": true,
    "speed": 1.0
  }'

import { SixtyDBClient } from "60db";

const client = new SixtyDBClient("your-api-key");

const audio = await client.textToSpeech({
  text: "Hello, world! This is a test of the text to speech API.",
  voice_id: "default-voice",
  enhance: true,
  speed: 1.0,
});

// audio is an ArrayBuffer

from sixtydb import SixtyDBClient

client = SixtyDBClient('your-api-key')

audio = client.text_to_speech(
    text='Hello, world! This is a test of the text to speech API.',
    voice_id='default-voice',
    enhance=True,
    speed=1.0
)

# Save to file
with open('output.mp3', 'wb') as f:
    f.write(audio)

Response

{
  "success": true,
  "message": "Audio generated successfully",
  "audio_base64": "SUQzBAAAAAAAI1RTU0UAAAAPAAADTGF2ZjU4Ljc2LjEwMAAAAAAAAAAAAAAA...",
  "sample_rate": 24000,
  "duration_seconds": 3.5,
  "encoding": "mp3",
  "output_format": "mp3"
}