Text to Speech (Lightning)

Quickstart

View as Markdown

Step 1: Get Your API Key

In the Smallest AI console, select API Keys from the left sidebar under Developer.

Smallest AI dashboard with API Keys highlighted under Developer section in the left sidebar

Click Create API Key in the top-right corner, enter a name, and click Create API Key to confirm.

API Keys page showing the Create API Key button Create New API Key dialog with API Name field and Create API Key button

The new key appears in your dashboard. Click the copy icon to copy it.

API Keys dashboard showing the newly created key with copy icon highlighted

Export the key in your terminal:

$export SMALLEST_API_KEY="your-api-key-here"
New to Smallest AI? Sign up here first.

Step 2: Hear Audio in 30 Seconds

Paste this in your terminal — no install required:

$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 from Smallest AI. This is Lightning v3.1 Pro.", "voice_id": "meher", "model": "lightning_v3.1_pro", "sample_rate": 24000, "output_format": "wav"}' \
>  --output hello.wav

Play hello.wav — it should sound like this:

That’s broadcast-quality TTS with ~200ms TTFB.

The model field selects which Lightning pool serves the request — lightning_v3.1_pro is the new premium pool with a curated voice catalog. Omit the field or pass "model": "lightning_v3.1" to use the standard pool (more voices, plus voice cloning).

Step 3: Build It Into Your App

$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": "Modern problems require modern solutions.",
>    "voice_id": "meher",
>    "model": "lightning_v3.1_pro",
>    "sample_rate": 24000,
>    "speed": 1.0,
>    "language": "en",
>    "output_format": "wav"
>  }' --output output.wav

The smallestai Python SDK’s synchronous WavesClient.synthesize() is being updated. Use the requests example above until the next SDK release.

Full runnable source files: Python | JavaScript | cURL

Step 4: Explore More

Lightning v3.1 Pro

Premium voice catalog across American, British, and Indian accents. Pass model: lightning_v3.1_pro to use.

Voices & Languages

Browse 217 voices across 12 languages on the standard pool — English, Hindi, Spanish, and 9 Indian languages.

Streaming TTS

Real-time audio streaming via WebSocket for voice assistants.

Voice Cloning

Clone any voice from just 5-15 seconds of audio (standard pool only).

Key Parameters

ParameterTypeDefaultDescription
textstringrequiredText to synthesize (max ~250 chars recommended)
voice_idstringrequiredVoice to use (e.g., meher, magnus)
modelstringlightning_v3.1TTS pool: lightning_v3.1 (standard) or lightning_v3.1_pro
sample_rateint441008000, 16000, 24000, or 44100 Hz
speedfloat1.0Speech rate: 0.5 to 2.0
languagestringenen, hi, es, ta, or auto (per voice; see voice tags via GET /waves/v1/lightning-v3.1/get_voices)
output_formatstringpcmpcm, wav, mp3, ulaw, or alaw

Need Help?

Join the Community

Ask questions, share what you’re building, and connect with other developers on Discord.

If you need direct assistance, reach out at support@smallest.ai.