Built for voice agents that can't wait 600ms

Hexgrad: Kokoro 82M

hexgrad/kokoro-82m
active tts 1 provider
Playground

Hexgrad Kokoro-82M is an open-weight 82M-parameter text-to-speech model (StyleTTS 2 + ISTFTNet) delivering large-model quality at low cost, hosted on Together AI.

AuthorHexgrad
Languages8 languages
VoicesLoading...
Response formatsSynchronous: MP3 · WAV · PCM
Streaming: PCM
Statusactive

Providers

Different providers can host the same model. Choose one provider when you need a fixed backend, or let routing select among them.

ProviderSlugPer 1k charactersLatencyiFor TTS, latency is measured as time to first byte of audio. For STT, latency is measured as time to first token.ModesUptime
Together AI 7 params
together
$0.01
—
Synchronous · Streaming

Supported languages

8 languages
English en
Japanese ja
Chinese (Mandarin) zh
Spanish es
French fr
Hindi hi
Italian it
Portuguese (Brazil) pt

Voices

Features

Text to speech

Generates spoken audio from text input.

text_to_speech
Streaming

Streaming TTS over HTTP and WebSocket.

streaming
Synchronous

Synthesizes speech from fully-submitted text in a single synchronous request.

synchronous
Voice mixing

Together supports mixing voices with + (e.g. af_bella+af_heart).

voice_mixing

Code

Client
Mode
Language

ElevenLabs SDK streaming TTS

Routes the ElevenLabs SDK through allmodels and streams the audio response.

import { ElevenLabsClient } from "elevenlabs";

const client = new ElevenLabsClient({
  apiKey: process.env.ALLMODELS_API_KEY,
  baseUrl: "https://api.allmodels.io/el"
});

const stream = await client.textToSpeech.stream("voice_id", {
  text: "I'm sorry, Dave. I'm afraid I can't do that.",
  modelId: "hexgrad/kokoro-82m",
  outputFormat: "mp3_44100_128"
}, {
  queryParams: {
    provider: {
      "only": [
        "together"
      ]
    }
  }
});

const reader = stream.getReader();
for (;;) {
  const { done, value } = await reader.read();
  if (done) break;
  // Write value to your response, file, or audio playback pipeline.
}