Audio

import { ModelGates } from '@modelgates/sdk';import fs from "fs/promises"; const modelgates = new ModelGates({  apiKey: '{}',}); async function encodeAudioToBase64(audioPath: string): Promise<string> {  const audioBuffer = await fs.readFile(audioPath);  return audioBuffer.toString("base64");} // Read and encode the audio fileconst audioPath = "path/to/your/audio.wav";const base64Audio = await encodeAudioToBase64(audioPath); const result = await modelgates.chat.send({  model: "{}",  messages: [    {      role: "user",      content: [        {          type: "text",          text: "Please transcribe this audio file.",        },        {          type: "input_audio",          inputAudio: {            data: base64Audio,            format: "wav",          },        },      ],    },  ],  stream: false,}); console.log(result);

import requestsimport jsonimport base64 def encode_audio_to_base64(audio_path):    with open(audio_path, "rb") as audio_file:        return base64.b64encode(audio_file.read()).decode('utf-8') url = "https://modelgates.ai/api/v1/chat/completions"headers = {    "Authorization": f"Bearer {API_KEY_REF}",    "Content-Type": "application/json"} # Read and encode the audio fileaudio_path = "path/to/your/audio.wav"base64_audio = encode_audio_to_base64(audio_path) messages = [    {        "role": "user",        "content": [            {                "type": "text",                "text": "Please transcribe this audio file."            },            {                "type": "input_audio",                "input_audio": {                    "data": base64_audio,                    "format": "wav"                }            }        ]    }] payload = {    "model": "{{MODEL}}",    "messages": messages} response = requests.post(url, headers=headers, json=payload)print(response.json())

import fs from "fs/promises"; async function encodeAudioToBase64(audioPath: string): Promise<string> {  const audioBuffer = await fs.readFile(audioPath);  return audioBuffer.toString("base64");} // Read and encode the audio fileconst audioPath = "path/to/your/audio.wav";const base64Audio = await encodeAudioToBase64(audioPath); const response = await fetch("https://modelgates.ai/api/v1/chat/completions", {  method: "POST",  headers: {    Authorization: `Bearer ${API_KEY_REF}`,    "Content-Type": "application/json",  },  body: JSON.stringify({    model: "{{MODEL}}",    messages: [      {        role: "user",        content: [          {            type: "text",            text: "Please transcribe this audio file.",          },          {            type: "input_audio",            input_audio: {              data: base64Audio,              format: "wav",            },          },        ],      },    ],  }),}); const data = await response.json();console.log(data);

import requestsimport jsonimport base64 url = "https://modelgates.ai/api/v1/chat/completions"headers = {    "Authorization": f"Bearer {API_KEY_REF}",    "Content-Type": "application/json"} payload = {    "model": "{{MODEL}}",    "messages": [        {            "role": "user",            "content": "Say hello in a friendly tone."        }    ],    "modalities": ["text", "audio"],    "audio": {        "voice": "alloy",        "format": "wav"    },    "stream": True} # Audio output requires streaming — the response is delivered as SSE chunksresponse = requests.post(url, headers=headers, json=payload, stream=True) audio_data_chunks = []transcript_chunks = [] for line in response.iter_lines():    if not line:        continue    decoded = line.decode("utf-8")    if not decoded.startswith("data: "):        continue    data = decoded[len("data: "):]    if data.strip() == "[DONE]":        break    chunk = json.loads(data)    delta = chunk["choices"][0].get("delta", {})    audio = delta.get("audio", {})    if audio.get("data"):        audio_data_chunks.append(audio["data"])    if audio.get("transcript"):        transcript_chunks.append(audio["transcript"]) transcript = "".join(transcript_chunks)print(f"Transcript: ") # Combine and decode the base64 audio chunks, then savefull_audio_b64 = "".join(audio_data_chunks)audio_bytes = base64.b64decode(full_audio_b64)with open("output.wav", "wb") as f:    f.write(audio_bytes)

const response = await fetch("https://modelgates.ai/api/v1/chat/completions", {  method: "POST",  headers: {    Authorization: `Bearer ${API_KEY_REF}`,    "Content-Type": "application/json",  },  body: JSON.stringify({    model: "{{MODEL}}",    messages: [      {        role: "user",        content: "Say hello in a friendly tone.",      },    ],    modalities: ["text", "audio"],    audio: {      voice: "alloy",      format: "wav",    },    stream: true,  }),}); // Audio output requires streaming — parse the SSE chunksconst reader = response.body!.getReader();const decoder = new TextDecoder(); const audioDataChunks: string[] = [];const transcriptChunks: string[] = [];let buffer = ""; while (true) {  const { done, value } = await reader.read();  if (done) break;   buffer += decoder.decode(value, { stream: true });  const lines = buffer.split("\n");  buffer = lines.pop()!; // keep incomplete line in buffer   for (const line of lines) {    if (!line.startsWith("data: ")) continue;    const data = line.slice("data: ".length).trim();    if (data === "[DONE]") break;     const chunk = JSON.parse(data);    const audio = chunk.choices?.[0]?.delta?.audio;    if (audio?.data) audioDataChunks.push(audio.data);    if (audio?.transcript) transcriptChunks.push(audio.transcript);  }} const transcript = transcriptChunks.join("");console.log(`Transcript: $`); // audioDataChunks joined together is the full base64-encoded audioconst fullAudioB64 = audioDataChunks.join("");

{  "choices": [    {      "delta": {        "audio": {          "data": "<base64-encoded audio chunk>",          "transcript": "Hello"        }      }    }  ]}