Sync & Async Synthesis

Generate speech via the REST API - synchronously (one request, complete audio) or asynchronously (multiple requests in parallel).

Sample output (sync, voice: meher, model: lightning_v3.1_pro):

Requirements

• An API key from the Smallest AI Console
• For Python: requests
• For JavaScript: Node.js 18+ (built-in fetch)

$
export SMALLEST_API_KEY="your-api-key-here"

Synchronous Text to Speech

Send text, receive complete audio in the response:

$
curl -X POST "https://api.smallest.ai/waves/v1/tts" \
>
  -H "Authorization: Bearer $SMALLEST_API_KEY" \
>
  -H "Content-Type: application/json" \
>
  -H "Accept: audio/wav" \
>
  -d '{
>
    "text": "Hello, this is a test of synchronous speech synthesis.",
>
    "voice_id": "meher",
>
    "model": "lightning_v3.1_pro",
>
    "sample_rate": 24000,
>
    "output_format": "wav"
>
  }' --output sync_output.wav

Asynchronous Text to Speech

For concurrent requests (e.g., generating multiple audio files in parallel):

1
import os
2
import asyncio
3
import aiohttp
4
5
API_KEY = os.environ["SMALLEST_API_KEY"]
6
URL = "https://api.smallest.ai/waves/v1/tts"
7
8
async def synthesize(session, text, filename):
9
    async with session.post(URL, headers={
10
        "Authorization": f"Bearer {API_KEY}",
11
        "Content-Type": "application/json",
12
        "Accept": "audio/wav",
13
    }, json={
14
        "text": text,
15
        "voice_id": "meher",
16
        "model": "lightning_v3.1_pro",
17
        "sample_rate": 24000,
18
        "output_format": "wav",
19
    }) as resp:
20
        audio = await resp.read()
21
        with open(filename, "wb") as f:
22
            f.write(audio)
23
        print(f"Saved {filename}")
24
25
async def main():
26
    async with aiohttp.ClientSession() as session:
27
        await asyncio.gather(
28
            synthesize(session, "First sentence.", "async_1.wav"),
29
            synthesize(session, "Second sentence.", "async_2.wav"),
30
            synthesize(session, "Third sentence.", "async_3.wav"),
31
        )
32
33
asyncio.run(main())

Python SDK

The smallestai Python SDK wraps the same endpoint. client.waves.synthesize_tts returns audio byte chunks; join them to get the full file. AsyncSmallestAI provides the same methods for async code.

1
from smallestai import SmallestAI
2
3
client = SmallestAI()  # reads SMALLEST_API_KEY from the environment
4
5
audio = b"".join(client.waves.synthesize_tts(
6
    text="Hello, this is a test of synchronous speech synthesis.",
7
    voice_id="meher",
8
    model="lightning_v3.1_pro",
9
    sample_rate=24000,
10
    output_format="wav",
11
))
12
13
with open("sync_output.wav", "wb") as f:
14
    f.write(audio)

For streaming synthesis via WebSocket or SSE, see Streaming TTS.

Parameters

You can override any parameter per request:

1
# ci:skip — fragment; assumes URL/headers/requests from the synchronous example above
2
# Override speed and sample rate for a single call
3
response = requests.post(URL, headers=headers, json={
4
    "text": "Fast and high quality.",
5
    "voice_id": "magnus",
6
    "speed": 1.5,
7
    "sample_rate": 44100,
8
    "output_format": "mp3",
9
})

When to Use Each Mode

• Synchronous: Real-time voice assistants, chatbot responses, single audio generation
• Asynchronous: Batch processing, generating multiple audio files, audiobook chapters, concurrent API calls

For real-time streaming where audio starts playing before generation completes, see Streaming TTS.

Need Help?

Check out the API Reference for the full endpoint specification, or ask on Discord.