Smallest AI

Smallest AI builds ultra-low-latency voice infrastructure - the Waves text-to-speech engine (Lightning / Lightning v2 models) for realtime speech synthesis and instant voice cloning, plus the Atoms platform for building and deploying production voice agents. The Waves REST API at https://waves-api.smallest.ai/api/v1 generates speech with sub-100ms latency, supports SSE and WebSocket streaming, and exposes voice listing and cloning via a Bearer-authenticated interface.

4 APIs 0 Features

AIText to SpeechVoiceRealtimeVoice Agents

APIs

Smallest AI Text-to-Speech (Waves)

Synthesizes natural speech from text with the Lightning family of models (sub-100ms latency, up to 44.1 kHz) via POST /lightning/get_speech, with configurable voice, sample rate...

Smallest AI Streaming / Realtime TTS

Realtime, low-latency text-to-speech delivered as base64 audio chunks over HTTP Server-Sent Events (POST /lightning-v2/get_speech/stream) and over a bidirectional WebSocket (wss...

Smallest AI Voices / Cloning

Lists available prebuilt voices, clones a new voice from a short audio sample, lists cloned voices, and deletes cloned voices for use as voice_id values in synthesis requests.

Smallest AI Atoms (Voice Agents)

The Atoms platform for building, testing, and deploying production voice agents - orchestrating Waves TTS and Pulse STT with LLM-driven conversation flows, exposed through a dev...

Collections

Smallest AI Waves API

OPEN

Pricing Plans

Smallest Ai Plans Pricing

4 plans

PLANS

Rate Limits

Smallest Ai Rate Limits

3 limits

RATE LIMITS

FinOps

Smallest Ai Finops

FINOPS

Event Specifications

Smallest AI Waves Realtime TTS (WebSocket)

Realtime, bidirectional text-to-speech over WebSocket for the Smallest AI Waves Lightning v2 model. The client opens a WebSocket connection, sends one or more JSON text payloads...

ASYNCAPI

Resources

👥

GitHubOrganization

Sources

opencollection: 1.0.0
info:
  name: Smallest AI Waves API
  version: '1.0'
request:
  auth:
    type: bearer
    token: '{{bearerToken}}'
items:
- info:
    name: Text to Speech
    type: folder
  items:
  - info:
      name: Synthesize speech from text.
      type: http
    http:
      method: POST
      url: https://waves-api.smallest.ai/api/v1/lightning/get_speech
      body:
        type: json
        data: "{\n  \"text\": \"Modern problems require modern solutions.\",\n  \"voice_id\": \"meher\",\n  \"model\": \"\
          lightning\",\n  \"sample_rate\": 24000,\n  \"speed\": 1.0,\n  \"language\": \"en\",\n  \"output_format\": \"wav\"\
          \n}"
    docs: Generates an audio file from the input text using a Lightning TTS model and the specified voice.
  - info:
      name: Stream synthesized speech (SSE).
      type: http
    http:
      method: POST
      url: https://waves-api.smallest.ai/api/v1/lightning-v2/get_speech/stream
      body:
        type: json
        data: "{\n  \"text\": \"Modern problems require modern solutions.\",\n  \"voice_id\": \"meher\",\n  \"model\": \"\
          lightning-v2\",\n  \"sample_rate\": 24000\n}"
    docs: Streams synthesized speech in realtime as Server-Sent Events whose data frames carry base64-encoded audio chunks.
      The same path is also available as a WebSocket (wss) endpoint.
- info:
    name: Voices
    type: folder
  items:
  - info:
      name: List available voices.
      type: http
    http:
      method: GET
      url: https://waves-api.smallest.ai/api/v1/lightning/get_voices
    docs: Returns the catalog of prebuilt voices available for synthesis.
  - info:
      name: Clone a voice.
      type: http
    http:
      method: POST
      url: https://waves-api.smallest.ai/api/v1/lightning/add_voice
      body:
        type: multipart-form
        data: []
    docs: Creates a new cloned voice from a short reference audio sample.
  - info:
      name: List cloned voices.
      type: http
    http:
      method: GET
      url: https://waves-api.smallest.ai/api/v1/lightning/get_cloned_voices
    docs: Returns the voices that the authenticated account has cloned.
  - info:
      name: Delete a cloned voice.
      type: http
    http:
      method: DELETE
      url: https://waves-api.smallest.ai/api/v1/lightning/delete_voice/:voiceId
    docs: Permanently deletes a previously cloned voice owned by the account.
bundled: true