Text to Speech Stream

Stream text to speech with real-time audio chunks

POST /tts-stream

cURL

curl -X POST https://api.60db.ai/tts-stream \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "This is a longer text that will be streamed in real-time.",
    "voice_id": "default-voice"
  }' \
  --no-buffer

import { SixtyDBClient } from "60db";

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

await client.textToSpeechStream(
  {
    text: "This is a longer text that will be streamed in real-time.",
    voice_id: "default-voice",
  },
  {
    onChunk: (chunk) => {
      console.log("Received chunk:", chunk.length, "bytes");
      // Play or process the audio chunk
    },
    onComplete: () => {
      console.log("Streaming complete");
    },
    onError: (error) => {
      console.error("Error:", error);
    },
  },
);

from sixtydb import SixtyDBClient

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

def handle_chunk(chunk):
    print(f"Received {len(chunk)} bytes")
    # Play or process the audio chunk

def handle_complete():
    print("Streaming complete")

def handle_error(error):
    print(f"Error: {error}")

client.text_to_speech_stream(
    text='This is a longer text that will be streamed in real-time.',
    on_chunk=handle_chunk,
    on_complete=handle_complete,
    on_error=handle_error,
    voice_id='default-voice'
)

Chunk Response

{"type":"chunk","result":{"audioContent":"SUQzBAAAAAAAI1RTU0UAAAAPAAADTGF2ZjU4..."}}
{"type":"chunk","result":{"audioContent":"//uQxAAAAAAAAAAAAAAASW5mbwAAAA8AAAAGAAA..."}}
{"type":"complete"}

{ "type": "error", "message": "Invalid voice_id" }

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

enhance · boolean · default: "true"

Enable audio enhancement

speed · number · default: "1.0"

Speech speed (0.5 to 2.0)

Response

The response is streamed as newline-delimited JSON (NDJSON). Each line contains a JSON object:

Chunk Object

type · string

Type of message: “chunk”, “complete”, or “error”

result · object

Contains the audio chunk data

result.audioContent · string

Base64-encoded audio chunk

message · string

Error message (only for error type)

cURL

curl -X POST https://api.60db.ai/tts-stream \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "This is a longer text that will be streamed in real-time.",
    "voice_id": "default-voice"
  }' \
  --no-buffer

import { SixtyDBClient } from "60db";

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

await client.textToSpeechStream(
  {
    text: "This is a longer text that will be streamed in real-time.",
    voice_id: "default-voice",
  },
  {
    onChunk: (chunk) => {
      console.log("Received chunk:", chunk.length, "bytes");
      // Play or process the audio chunk
    },
    onComplete: () => {
      console.log("Streaming complete");
    },
    onError: (error) => {
      console.error("Error:", error);
    },
  },
);

from sixtydb import SixtyDBClient

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

def handle_chunk(chunk):
    print(f"Received {len(chunk)} bytes")
    # Play or process the audio chunk

def handle_complete():
    print("Streaming complete")

def handle_error(error):
    print(f"Error: {error}")

client.text_to_speech_stream(
    text='This is a longer text that will be streamed in real-time.',
    on_chunk=handle_chunk,
    on_complete=handle_complete,
    on_error=handle_error,
    voice_id='default-voice'
)

Chunk Response

{"type":"chunk","result":{"audioContent":"SUQzBAAAAAAAI1RTU0UAAAAPAAADTGF2ZjU4..."}}
{"type":"chunk","result":{"audioContent":"//uQxAAAAAAAAAAAAAAASW5mbwAAAA8AAAAGAAA..."}}
{"type":"complete"}

{ "type": "error", "message": "Invalid voice_id" }

Use Cases

Streaming is ideal for:

• Real-time applications: Voice assistants, chatbots
• Long-form content: Articles, books, documents
• Low latency: Start playing audio before generation completes
• Progressive enhancement: Display text while generating audio