|
|
from flask import Flask, request, jsonify, Response, stream_with_context |
|
|
import requests |
|
|
import uuid |
|
|
import json |
|
|
import time |
|
|
import os |
|
|
import re |
|
|
import base64 |
|
|
|
|
|
API_KEY = os.getenv("API_KEY", "linux.do") |
|
|
|
|
|
app = Flask(__name__) |
|
|
|
|
|
@app.before_request |
|
|
def check_api_key(): |
|
|
key = request.headers.get("Authorization") |
|
|
if key != "Bearer "+API_KEY: |
|
|
return jsonify({"success": False, "message": "Unauthorized: Invalid API key"}), 403 |
|
|
|
|
|
@app.route('/v1/models', methods=['GET']) |
|
|
def get_models(): |
|
|
|
|
|
headers = { |
|
|
"Content-Type": "application/json", |
|
|
"Authorization": "Bearer "+API_KEY |
|
|
} |
|
|
|
|
|
response = requests.get( |
|
|
'https://text.pollinations.ai/models', |
|
|
headers=headers |
|
|
) |
|
|
|
|
|
name_mapping = { |
|
|
"claude-hybridspace": "claude hybridspace", |
|
|
"gemini-thinking": "gemini thinking", |
|
|
"gemini": "openai/gemini" |
|
|
} |
|
|
|
|
|
models_data = response.json() |
|
|
current_timestamp = int(time.time()) |
|
|
converted_data = { |
|
|
"object": "list", |
|
|
"data": [ |
|
|
{ |
|
|
"id": name_mapping.get(model["name"], model["name"]), |
|
|
"object": "model", |
|
|
"created": current_timestamp, |
|
|
"owned_by": "openai" if "openai" in model["name"] else "third_party", |
|
|
"permissions": [], |
|
|
"root": name_mapping.get(model["name"], model["name"]), |
|
|
"parent": None, |
|
|
"capabilities": { |
|
|
"vision": model.get("vision", False), |
|
|
"audio": model.get("audio", False), |
|
|
"reasoning": model.get("reasoning", True) |
|
|
}, |
|
|
"description": model["description"] |
|
|
} |
|
|
for model in models_data |
|
|
] |
|
|
} |
|
|
return converted_data |
|
|
|
|
|
|
|
|
def encode_audio_base64(file_path): |
|
|
""" Reads an audio file and encodes it as base64. """ |
|
|
with open(file_path, "rb") as audio_file: |
|
|
return base64.b64encode(audio_file.read()).decode("utf-8") |
|
|
|
|
|
def transcribe_audio(base64_audio, file_format, model="openai-audio"): |
|
|
""" Sends base64 encoded audio for transcription using OpenAI-compatible API. """ |
|
|
API_URL = "https://text.pollinations.ai/openai" |
|
|
API_KEY = "your_api_key_here" |
|
|
|
|
|
headers = {"Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json"} |
|
|
payload = { |
|
|
"model": model, |
|
|
"messages": [ |
|
|
{"role": "user", "content": [ |
|
|
{"type": "text", "text": "Transcribe this audio exactly"}, |
|
|
{"type": "input_audio", "input_audio": {"data": base64_audio, "format": file_format}} |
|
|
]} |
|
|
] |
|
|
} |
|
|
|
|
|
response = requests.post(API_URL, json=payload, headers=headers) |
|
|
print(response.text) |
|
|
if response.ok: |
|
|
return response.json().get("choices", [{}])[0].get("message", {}).get("content", "No transcription found.") |
|
|
return None |
|
|
|
|
|
@app.route("/v1/audio/transcriptions", methods=["POST"]) |
|
|
def handle_transcription(): |
|
|
""" Flask API endpoint to handle audio transcription requests. """ |
|
|
if "file" not in request.files: |
|
|
return jsonify({"error": "No file provided"}), 400 |
|
|
|
|
|
file = request.files["file"] |
|
|
model = request.form.get("model", "openai-audio") |
|
|
print(model) |
|
|
file_format = "mp3" if file.filename.lower().endswith(".mp3") else "wav" |
|
|
base64_audio = base64.b64encode(file.read()).decode("utf-8") |
|
|
|
|
|
transcription = transcribe_audio(base64_audio, file_format,model) |
|
|
|
|
|
if transcription: |
|
|
return jsonify({"text": transcription}) |
|
|
return jsonify({"error": "Transcription failed"}), 500 |
|
|
|
|
|
if __name__ == '__main__': |
|
|
app.run(host='0.0.0.0', port=5200, debug=True) |
