Ax Audio

import { ai } from '@ax-llm/ax';

const llm = ai({ name: 'openai', apiKey: process.env.OPENAI_APIKEY! });

const transcript = await llm.transcribe({
  audio: { data: base64Wav, format: 'wav' },
  model: 'gpt-4o-mini-transcribe',
  language: 'en',
  prompt: 'Product support call',
});

const speech = await llm.speak({
  text: transcript.text,
  model: 'gpt-4o-mini-tts',
  voice: 'alloy',
  format: 'mp3',
});

console.log(transcript.text);
console.log(speech.data);
console.log(speech.transcript);

import { ai, ax } from '@ax-llm/ax';

const llm = ai({ name: 'openai', apiKey: process.env.OPENAI_APIKEY! });
const say = ax('question:string -> speech:audio, summary:string');

const result = await say.forward(
  llm,
  { question: 'Explain retries in one sentence.' },
  {
    speech: {
      speak: { voice: 'alloy', format: 'mp3' },
      fields: {
        speech: { voice: 'alloy' },
      },
    },
  }
);

console.log(result.summary);
console.log(result.speech.data);
console.log(result.speech.mimeType);
console.log(result.speech.transcript);

import { agent, ai } from '@ax-llm/ax';

const llm = ai({ name: 'openai', apiKey: process.env.OPENAI_APIKEY! });

const voiceAgent = agent(
  'recording:audio, question:string -> speech:audio, summary:string',
  {
    agentIdentity: {
      name: 'Voice Assistant',
      description: 'Answers spoken requests with spoken and written output',
    },
    contextFields: [],
  }
);

const result = await voiceAgent.forward(
  llm,
  {
    recording: { data: base64Wav, format: 'wav' },
    question: 'What should I do next?',
  },
  {
    speech: {
      transcribe: { model: 'gpt-4o-mini-transcribe' },
      speak: { voice: 'alloy', format: 'mp3' },
    },
  }
);

console.log(result.summary);
console.log(result.speech.data);

const res = await llm.chat({
  chatPrompt: [{ role: 'user', content: 'Say hello out loud.' }],
  modelConfig: {
    audio: { output: { enabled: true, voice: 'alloy', format: 'wav' } },
  },
});

console.log(res.results[0]?.content);
console.log(res.results[0]?.audio?.data);
console.log(res.results[0]?.audio?.transcript);

type AxAudioFormat =
  | 'wav'
  | 'mp3'
  | 'flac'
  | 'opus'
  | 'aac'
  | 'pcm16'
  | 'pcm'
  | 'ogg'
  | 'raw'
  | 'mulaw'
  | 'ulaw'
  | 'alaw';

type AxSpeechConfig = {
  transcribe?: {
    model?: string;
    language?: string;
    prompt?: string;
  };
  speak?: {
    model?: string;
    voice?: string;
    format?: AxAudioFormat;
  };
  fields?: Record<
    string,
    {
      model?: string;
      voice?: string;
      format?: AxAudioFormat;
    }
  >;
};

import { ai, axAIOpenAIAudioDefaultConfig } from '@ax-llm/ax';

const openai = ai({
  name: 'openai',
  apiKey: process.env.OPENAI_APIKEY!,
  config: axAIOpenAIAudioDefaultConfig(),
});

const res = await openai.chat({
  chatPrompt: [
    {
      role: 'user',
      content: [
        { type: 'text', text: 'What is in this recording?' },
        { type: 'audio', data: base64Wav, format: 'wav' },
      ],
    },
  ],
});

console.log(res.results[0]?.content);
console.log(res.results[0]?.audio?.data);

import WebSocket from 'ws';
import { ai, axAIOpenAIRealtimeDefaultConfig } from '@ax-llm/ax';

const openai = ai({
  name: 'openai',
  apiKey: process.env.OPENAI_APIKEY!,
  config: axAIOpenAIRealtimeDefaultConfig(),
});

const stream = await openai.chat(
  {
    chatPrompt: [{ role: 'user', content: 'Say hello out loud.' }],
  },
  { stream: true, webSocket: WebSocket }
);

await openai.chat({
  chatPrompt: [
    { role: 'assistant', audio: { id: previousAudioId } },
    { role: 'user', content: 'Repeat that more slowly.' },
  ],
});