Introduction

Smallest AI builds speech AI models and APIs. Generate natural speech, transcribe audio in real-time, and clone voices — all through simple API calls.

Models

Lightning (Text-to-Speech)

Generate speech with 217 voices across 12 languages, 44.1 kHz audio, and ~200ms TTFB. English, Hindi, Spanish, plus 9 Indian languages.

Pulse (Speech-to-Text)

Transcribe audio in real-time or from files. 38 languages, speaker diarization, emotion detection.

Electron (LLM)

OpenAI-compatible chat completions. Sub-300 ms TTFT, 32K context, 70 languages with first-class Indic support, voice-agent-optimized tool calling, and automatic prefix caching.

Get Your API Key

Create an account

Go to app.smallest.ai and sign up with email or Google.

Navigate to API Keys

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

Create and copy your key

Click the Create API Key button in the top-right corner.

API Keys page showing the Create API Key button in the top-right corner

Enter a name for the key and click Create API Key.

Create New API Key dialog with API Name field and Create API Key button

Use your key

The newly created key appears in your API Keys dashboard. Click the copy icon to copy it.

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

Set it in your terminal:

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

Try It Now

Generate speech (Lightning TTS)

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.", "voice_id": "meher", "model": "lightning_v3.1_pro", "sample_rate": 24000, "output_format": "wav"}' \
>   --output hello.wav

Play hello.wav — you should hear the same quality as the sample above.

Transcribe audio (Pulse STT)

$ curl -X POST "https://api.smallest.ai/waves/v1/pulse/get_text?language=en" \
>   -H "Authorization: Bearer $SMALLEST_API_KEY" \
>   -H "Content-Type: application/json" \
>   -d '{"url": "https://github.com/smallest-inc/cookbook/raw/main/speech-to-text/getting-started/samples/audio.wav"}'

You’ll get back:

1 {
2   "transcription": "This is a sample audio file for testing speech to text transcription with the Pulse API."
3 }

Next Steps

TTS Quickstart

Full guide with Python, JavaScript, and SDK examples.

STT Quickstart

Transcribe files and stream audio in real-time.

Model Cards

Benchmarks, specs, and capabilities.

Cookbooks

Production-ready example projects.

Showcase

See what developers have built with Smallest AI.

GitHub

Open-source cookbook with 20+ examples.

Community & Support

Join Discord

Ask questions, share projects, and connect with other developers.

Email Support

Reach our team directly for technical assistance.

$	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.", "voice_id": "meher", "model": "lightning_v3.1_pro", "sample_rate": 24000, "output_format": "wav"}' \
>	--output hello.wav

1	{
2	"transcription": "This is a sample audio file for testing speech to text transcription with the Pulse API."
3	}