ارسال و دریافت صدا — Audio

package main

import (
	"bytes"
	"encoding/base64"
	"encoding/json"
	"fmt"
	"net/http"
	"os"
)

func encodeAudioToBase64(audioPath string) (string, error) {
	raw, err := os.ReadFile(audioPath)
	if err != nil {
		return "", err
	}
	return base64.StdEncoding.EncodeToString(raw), nil
}

func main() {
	audioPath := "path/to/your/audio.wav"
	base64Audio, _ := encodeAudioToBase64(audioPath)

	payload := map[string]any{
		"model": "~google/gemini-2.5-flash",
		"messages": []any{
			map[string]any{
				"role": "user",
				"content": []any{
					map[string]any{"type": "text", "text": "Please transcribe this audio file."},
					map[string]any{
						"type": "input_audio",
						"input_audio": map[string]any{
							"data":   base64Audio,
							"format": "wav",
						},
					},
				},
			},
		},
		"stream": false,
	}
	body, _ := json.Marshal(payload)

	req, _ := http.NewRequest("POST", "https://app.asha-ai.ir/v1/chat/completions", bytes.NewReader(body))
	req.Header.Set("Authorization", "Bearer "+os.Getenv("ASHA_API_KEY"))
	req.Header.Set("Content-Type", "application/json")

	resp, err := http.DefaultClient.Do(req)
	if err != nil {
		panic(err)
	}
	defer resp.Body.Close()

	var result map[string]any
	_ = json.NewDecoder(resp.Body).Decode(&result)
	fmt.Println(result)
}

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 file
const audioPath = "path/to/your/audio.wav";
const base64Audio = await encodeAudioToBase64(audioPath);

const response = await fetch("https://app.asha-ai.ir/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.ASHA_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "~google/gemini-2.5-flash",
    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 fs from "fs/promises";

async function encodeAudioToBase64(audioPath) {
  const audioBuffer = await fs.readFile(audioPath);
  return audioBuffer.toString("base64");
}

// Read and encode the audio file
const audioPath = "path/to/your/audio.wav";
const base64Audio = await encodeAudioToBase64(audioPath);

const response = await fetch("https://app.asha-ai.ir/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.ASHA_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "~google/gemini-2.5-flash",
    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);

# Base64-encode your audio file
AUDIO_BASE64=$(base64 < audio.wav | tr -d 'n')

curl https://app.asha-ai.ir/v1/chat/completions 
  -H "Content-Type: application/json" 
  -H "Authorization: Bearer $ASHA_API_KEY" 
  -d '{
    "model": "~google/gemini-2.5-flash",
    "messages": [
      {
        "role": "user",
        "content": [
          { "type": "text", "text": "Please transcribe this audio file." },
          { "type": "input_audio", "input_audio": { "data": "'"$AUDIO_BASE64"'", "format": "wav" } }
        ]
      }
    ]
  }'

const response = await fetch("https://app.asha-ai.ir/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.ASHA_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "~openai/gpt-audio",
    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 chunks
const 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: ${transcript}`);

// audioDataChunks joined together is the full base64-encoded audio
const fullAudioB64 = audioDataChunks.join("");

curl -N https://app.asha-ai.ir/v1/chat/completions 
  -H "Content-Type: application/json" 
  -H "Authorization: Bearer $ASHA_API_KEY" 
  -d '{
    "model": "~openai/gpt-audio",
    "messages": [
      {
        "role": "user",
        "content": "Say hello in a friendly tone."
      }
    ],
    "modalities": ["text", "audio"],
    "audio": {
      "voice": "alloy",
      "format": "wav"
    },
    "stream": true
  }'