export OPENAI_API_KEY=your_telnyx_api_key
export OPENAI_BASE_URL=https://api.telnyx.com/v2/ai/openai

export OPENAI_BASE_URL='https://api.telnyx.com/v2/ai/openai'
export OPENAI_API_KEY='KEY***'

from openai import OpenAI

client = OpenAI()  # picks up env vars
chat_completion = client.chat.completions.create(
    model="zai-org/GLM-5.2",
    messages=[{"role": "user", "content": "Tell me about Telnyx"}],
    temperature=0.0,
    stream=True,
)

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("TELNYX_API_KEY"),
    base_url="https://api.telnyx.com/v2/ai/openai",
)
chat_completion = client.chat.completions.create(
    model="zai-org/GLM-5.2",
    messages=[{"role": "user", "content": "Tell me about Telnyx"}],
    temperature=0.0,
    stream=True,
)

chat_completion = client.chat.completions.create(
    model="zai-org/GLM-5.2",
    messages=[{"role": "user", "content": "Tell me about Telnyx"}],
)
message = chat_completion.choices[0].message

# Reasoning models populate reasoning_content; other models leave it None.
if getattr(message, "reasoning_content", None):
    print("reasoning:", message.reasoning_content)
print("answer:", message.content)

export TELNYX_API_KEY='KEY***'

import os
from anthropic import Anthropic

client = Anthropic(
    api_key="unused",  # placeholder — the gateway uses the Bearer header below
    base_url="https://api.telnyx.com/v2/ai/anthropic",
    default_headers={
        "Authorization": f"Bearer {os.environ['TELNYX_API_KEY']}",
    },
)

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  apiKey: "unused", // placeholder — the gateway uses the Bearer header below
  baseURL: "https://api.telnyx.com/v2/ai/anthropic",
  defaultHeaders: {
    Authorization: `Bearer ${process.env.TELNYX_API_KEY}`,
  },
});

import os
from anthropic import Anthropic

client = Anthropic(
    api_key="unused",
    base_url="https://api.telnyx.com/v2/ai/anthropic",
    default_headers={
        "Authorization": f"Bearer {os.environ['TELNYX_API_KEY']}",
    },
)

# Non-streaming
message = client.messages.create(
    model="zai-org/GLM-5.2",
    max_tokens=1024,
    system="You are a friendly chatbot.",
    messages=[
        {"role": "user", "content": "Tell me about Telnyx"}
    ],
)
print(message.content[0].text)

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  apiKey: "unused",
  baseURL: "https://api.telnyx.com/v2/ai/anthropic",
  defaultHeaders: {
    Authorization: `Bearer ${process.env.TELNYX_API_KEY}`,
  },
});

// Non-streaming
const message = await client.messages.create({
  model: "zai-org/GLM-5.2",
  max_tokens: 1024,
  system: "You are a friendly chatbot.",
  messages: [{ role: "user", content: "Tell me about Telnyx" }],
});
console.log(message.content[0].text);

curl -sS -X POST "https://api.telnyx.com/v2/ai/anthropic/v1/messages" \
  -H "Authorization: Bearer $TELNYX_API_KEY" \
  -H "Content-Type: application/json" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "zai-org/GLM-5.2",
    "max_tokens": 1024,
    "system": "You are a friendly chatbot.",
    "messages": [{"role": "user", "content": "Tell me about Telnyx"}]
  }'

import os
from anthropic import Anthropic

client = Anthropic(
    api_key="unused",
    base_url="https://api.telnyx.com/v2/ai/anthropic",
    default_headers={
        "Authorization": f"Bearer {os.environ['TELNYX_API_KEY']}",
    },
)

with client.messages.stream(
    model="zai-org/GLM-5.2",
    max_tokens=1024,
    system="You are a friendly chatbot.",
    messages=[{"role": "user", "content": "Tell me about Telnyx"}],
) as stream:
    for text in stream.text_stream:
        print(text, end="", flush=True)

const stream = await client.messages.stream({
  model: "zai-org/GLM-5.2",
  max_tokens: 1024,
  system: "You are a friendly chatbot.",
  messages: [{ role: "user", content: "Tell me about Telnyx" }],
});

for await (const event of stream) {
  if (event.type === "content_block_delta" && event.delta.type === "text_delta") {
    process.stdout.write(event.delta.text);
  }
}

import os
import json
from anthropic import Anthropic

client = Anthropic(
    api_key="unused",
    base_url="https://api.telnyx.com/v2/ai/anthropic",
    default_headers={
        "Authorization": f"Bearer {os.environ['TELNYX_API_KEY']}",
    },
)

tools = [
    {
        "name": "get_weather",
        "description": "Get the current weather in a given location.",
        "input_schema": {
            "type": "object",
            "properties": {
                "location": {"type": "string", "description": "City and state, e.g. San Francisco, CA"},
            },
            "required": ["location"],
        },
    }
]

response = client.messages.create(
    model="zai-org/GLM-5.2",
    max_tokens=1024,
    tools=tools,
    messages=[{"role": "user", "content": "What's the weather in Lisbon?"}],
)

# The model returns a tool_use content block
for block in response.content:
    if block.type == "tool_use":
        print(f"Tool: {block.name}")
        print(f"Input: {block.input}")

response = client.messages.create(
    model="zai-org/GLM-5.2",
    max_tokens=4096,
    messages=[{"role": "user", "content": "Exprove que 17 é primo."}],
    extra_body={
        "thinking": {"type": "enabled", "budget_tokens": 2048},
    },
)

# String system prompt
response = client.messages.create(
    model="zai-org/GLM-5.2",
    max_tokens=1024,
    system="You are a helpful assistant.",
    messages=[{"role": "user", "content": "Hello!"}],
)

# Array-style system prompt (cache_control, etc.)
response = client.messages.create(
    model="zai-org/GLM-5.2",
    max_tokens=1024,
    system=[
        {"type": "text", "text": "You are a helpful assistant.", "cache_control": {"type": "ephemeral"}},
    ],
    messages=[{"role": "user", "content": "Hello!"}],
)

response = client.messages.create(
    model="zai-org/GLM-5.2",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello!"}],
    extra_body={
        "billing_group_id": "6a09cdc3-8948-47f0-aa62-74ac943d6c58",
    },
)

pip install langchain-openai

import os
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    base_url="https://api.telnyx.com/v2/ai/openai",
    api_key=os.getenv("TELNYX_API_KEY"),
    model="zai-org/GLM-5.2",
)

for chunk in llm.stream("Help me plan my vacation"):
    print(chunk.content, end="", flush=True)

import os
from langchain_openai import ChatOpenAI
from langchain_core.tools import tool

@tool
def get_weather(location: str) -> str:
    """Get the current weather for a location."""
    return f"The weather in {location} is sunny and 72°F."

llm_with_tools = ChatOpenAI(
    base_url="https://api.telnyx.com/v2/ai/openai",
    api_key=os.getenv("TELNYX_API_KEY"),
    model="zai-org/GLM-5.2",
).bind_tools([get_weather])

result = llm_with_tools.invoke("What's the weather in Chicago?")
print(result.tool_calls)

from langchain_core.messages import HumanMessage

messages = [HumanMessage(content="Explain quantum computing in 3 sentences")]
for chunk in llm.stream(messages):
    print(chunk.content, end="", flush=True)

pip install llama-index-core llama-index-llms-openai-like

import os
from llama_index.llms.openai_like import OpenAILike
from llama_index.core.llms import ChatMessage

llm = OpenAILike(
    api_base="https://api.telnyx.com/v2/ai/openai",
    api_key=os.getenv("TELNYX_API_KEY"),
    model="zai-org/GLM-5.2",
    is_chat_model=True,
)

chat = llm.stream_chat([ChatMessage(role="user", content="Help me plan my vacation")])
for chunk in chat:
    print(chunk.delta, end="")

pip install crewai

export TELNYX_API_KEY=your_telnyx_api_key
export OPENAI_BASE_URL=https://api.telnyx.com/v2/ai/openai

import os
from crewai import Agent, Task, Crew, LLM

llm = LLM(
    model="zai-org/GLM-5.2",
    base_url="https://api.telnyx.com/v2/ai/openai",
    api_key=os.getenv("TELNYX_API_KEY"),
)

researcher = Agent(
    role="Research Analyst",
    goal="Find and analyze information",
    backstory="You are an experienced research analyst.",
    llm=llm,
)

writer = Agent(
    role="Technical Writer",
    goal="Write clear, accurate reports",
    backstory="You are a skilled technical writer.",
    llm=llm,
)

research_task = Task(
    description="Research the latest trends in AI infrastructure",
    agent=researcher,
)

write_task = Task(
    description="Write a summary report based on the research findings",
    agent=writer,
)

crew = Crew(agents=[researcher, writer], tasks=[research_task, write_task])
result = crew.kickoff()
print(result)

from crewai.tools import tool

@tool("Search the web")
def search_web(query: str) -> str:
    """Search the web for information."""
    return f"Results for: {query}"

researcher = Agent(
    role="Research Analyst",
    goal="Find and analyze information",
    backstory="You are an experienced research analyst.",
    llm=llm,
    tools=[search_web],
)

python -m venv venv
source venv/bin/activate

pip install -r requirements.txt
pip install livekit-plugins-telnyx

python agent.py download-files

from dotenv import load_dotenv
from livekit.agents import AutoSubscribe, JobContext, WorkerOptions, cli, voice, llm
from livekit.plugins import openai, silero, telnyx

load_dotenv()

async def entrypoint(ctx: JobContext):
    initial_ctx = llm.ChatContext().append(
        role="system",
        text=(
            "You are a helpful voice assistant powered by Telnyx. "
            "Keep responses short and conversational."
        ),
    )

    await ctx.connect(auto_subscribe=AutoSubscribe.AUDIO_ONLY)

    session = voice.AgentSession(
        llm=openai.LLM.with_telnyx(
            model="zai-org/GLM-5.2",
        ),
        vad=silero.VAD.load(),
        stt=telnyx.STT(),
        tts=telnyx.TTS(voice="Telnyx.NaturalHD.astra"),
        chat_ctx=initial_ctx,
    )
    session.start(ctx.room)

    await session.say("Hey, how can I help you today?", allow_interruptions=True)

if __name__ == "__main__":
    cli.run_app(WorkerOptions(entrypoint_fnc=entrypoint))

export TELNYX_API_KEY=<your Telnyx API key>
export LIVEKIT_URL=<your LiveKit server URL>
export LIVEKIT_API_KEY=<your LiveKit API key>
export LIVEKIT_API_SECRET=<your LiveKit API secret>

python agent.py dev

pip install livekit-plugins-telnyx

from livekit.plugins import telnyx

session = voice.AgentSession(
    stt=telnyx.STT(),
    # ... other plugins
)

from livekit.plugins import telnyx

session = voice.AgentSession(
    tts=telnyx.TTS(voice="Telnyx.NaturalHD.astra"),
    # ... other plugins
)

pip install openai

import os
from openai import OpenAI

client = OpenAI(
  api_key=os.getenv("TELNYX_API_KEY"),
  base_url="https://api.telnyx.com/v2/ai/openai",
)

chat_completion = client.chat.completions.create(
  messages=[
    {"role": "user", "content": "Tell me about Telnyx"}
  ],
  model="zai-org/GLM-5.2",
  stream=True
)

# GLM-5.2 is a reasoning model: it streams its thinking in `reasoning_content`
# before the final answer in `content`. Print both so you can see the reasoning.
reasoning_started = False
content_started = False
for chunk in chat_completion:
  delta = chunk.choices[0].delta
  if getattr(delta, "reasoning_content", None):
    if not reasoning_started:
      print("--- reasoning ---")
      reasoning_started = True
    print(delta.reasoning_content, end="", flush=True)
  if delta.content:
    if not content_started:
      print("\n--- answer ---")
      content_started = True
    print(delta.content, end="", flush=True)

import os

from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("TELNYX_API_KEY"),
    base_url="https://api.telnyx.com/v2/ai/openai",
)

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_current_weather",
            "description": "Get the current weather",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {
                        "type": "string",
                        "description": "The city and state, e.g. San Francisco, CA",
                    },
                    "unit": {
                        "type": "string",
                        "enum": ["celsius", "fahrenheit"],
                        "description": "The temperature unit to use",
                    },
                },
                "required": ["location", "unit"],
            },
        }
    }
]

messages = [
    {"role": "user", "content": "How is the weather in Chicago?"}
]

chat_completion = client.chat.completions.create(
    model="zai-org/GLM-5.2",
    messages=messages,
    tools=tools,
    tool_choice="auto"
)
print(chat_completion.choices[0].message)

ChatCompletionMessage(content=None, role='assistant', function_call=None, tool_calls=[ChatCompletionMessageToolCall(id='call_c31258d2-78a8-4566-b716-e3b2a774cbdb', function=Function(arguments='{"location": "Chicago", "unit": "fahrenheit"}', name='get_current_weather'), type='function')])

import inspect
import os
import json
from typing import Literal

from openai import OpenAI
from pydantic import create_model

def func_to_tool(f):
    kw = {
        n: (o.annotation, ... if o.default==inspect.Parameter.empty else o.default)
        for n, o in inspect.signature(f).parameters.items()
        }
    s = create_model(f.__name__, **kw).model_json_schema()
    tool_json = {
        "type": "function",
        "function": {
            "name": s["title"],
            "description": inspect.getdoc(f),
            "parameters": s
        }
    }
    return tool_json

TempUnit = Literal['celsius', 'fahrenheit']

def get_current_weather(location: str, unit: TempUnit = 'fahrenheit'):
    """Get the current weather in a given location"""
    if "tokyo" in location.lower():
        return json.dumps({"location": "Tokyo", "temperature": "10", "unit": unit})
    elif "san francisco" in location.lower():
        return json.dumps({"location": "San Francisco", "temperature": "72", "unit": unit})
    elif "chicago" in location.lower():
        return json.dumps({"location": "Chicago", "temperature": "22", "unit": unit})
    else:
        return json.dumps({"location": location, "temperature": "unknown"})

client = OpenAI(
    api_key=os.getenv("TELNYX_API_KEY"),
    base_url="https://api.telnyx.com/v2/ai/openai",
)
tools = [func_to_tool(get_current_weather)]
messages = [
    {"role": "user", "content": "How is the weather in Chicago?"}
]
chat_completion = client.chat.completions.create(
    model="zai-org/GLM-5.2",
    messages=messages,
    tools=tools,
    tool_choice="auto"
)
print(chat_completion.choices[0].message)

assistant_message = chat_completion.choices[0].message
tool_calls = assistant_message.tool_calls
content = assistant_message.content
if tool_calls:
    messages.append(assistant_message)
    available_functions = {"get_current_weather": get_current_weather}
    for tool_call in tool_calls:
        function_name = tool_call.function.name
        function_to_call = available_functions[function_name]
        function_args = json.loads(tool_call.function.arguments)
        function_response = function_to_call(**function_args)
        messages.append(
            {
                "tool_call_id": tool_call.id,
                "role": "tool",
                "name": function_name,
                "content": function_response,
            }
        )
    second_chat_completion = client.chat.completions.create(
        model="zai-org/GLM-5.2",
        messages=messages,
    )
    print(second_chat_completion.choices[0].message.content)
else:
    print(content)

It's 22°F in Chicago.

import asyncio
import inspect
import json
import os
from openai import AsyncOpenAI
from pydantic import create_model

# Configuration
API_KEY = os.getenv("TELNYX_API_KEY")
BASE_URL = "https://api.telnyx.com/v2/ai/openai"
MODEL = "zai-org/GLM-5.2"

client = AsyncOpenAI(api_key=API_KEY, base_url=BASE_URL)

async def sleep(seconds: int):
    """Sleep for a given number of seconds."""
    await asyncio.sleep(seconds)
    return f"I slept for {seconds} seconds!"

async def dream(subject: str):
    """Dream about a given subject."""
    chat_completion = await client.chat.completions.create(
        model=MODEL,
        messages=[
            {
                "role": "user",
                "content": f"BRIEFLY (one sentence max) describe a dream about {subject}"
            }
        ]
    )
    return chat_completion.choices[0].message.content

def func_to_tool(f):
    """Convert a function to a tool JSON schema."""
    kw = {
        n: (o.annotation, ... if o.default == inspect.Parameter.empty else o.default)
        for n, o in inspect.signature(f).parameters.items()
    }
    schema = create_model(f.__name__, **kw).model_json_schema()
    tool_json = {
        "type": "function",
        "function": {
            "name": schema["title"],
            "description": inspect.getdoc(f),
            "parameters": schema
        }
    }
    return tool_json

async def func_wrapper(func, tool_call_id, **kwargs):
    """Wrap a function to return its ID + name when executed."""
    result = await func(**kwargs)
    return tool_call_id, func.__name__, result

async def execute_tasks(tasks):
    """Execute asynchronous tasks and collect their results."""
    results = []
    for task in asyncio.as_completed(tasks):
        tool_call_id, func_name, result = await task
        print(f"Executed {func_name}, results: {result}")
        results.append(
            {
                "tool_call_id": tool_call_id,
                "role": "tool",
                "name": func_name,
                "content": result,
            }
        )
    return results

async def handle_tool_calls(chat_completion, function_map):
    """Handle streaming tool calls from chat completion."""
    tool_calls = []
    tasks = []
    tasked_tool_ids = set()

    async for chunk in chat_completion:
        delta = chunk.choices[0].delta
        if delta and delta.tool_calls:
            # We have detected tool calls from the LLM
            tcchunklist = delta.tool_calls
            for tcchunk in tcchunklist:
                index = tcchunk.index or 0
                if len(tool_calls) <= index:
                    # Based on the index, we have a new tool call
                    tool_calls.append(
                        {
                            "id": "",
                            "type": "function",
                            "function": {
                                "name": "",
                                "arguments": ""
                            }
                        }
                    )
                tc = tool_calls[index]

                if tcchunk.id:
                    tc["id"] += tcchunk.id
                if tcchunk.function.name:
                    tc["function"]["name"] += tcchunk.function.name
                    print(f"Detected function: {tcchunk.function.name}")
                if tcchunk.function.arguments:
                    tc["function"]["arguments"] += tcchunk.function.arguments
                    try:
                        kwargs = json.loads(tc["function"]["arguments"])
                    except json.JSONDecodeError:
                        # We don't have the full arguments JSON yet
                        continue
                    else:
                        if tc["id"] not in tasked_tool_ids:
                            func_name = tc["function"]["name"]
                            print(f"Executing {func_name} with {kwargs}")
                            wrapped_func = func_wrapper(function_map[func_name], tc["id"], **kwargs)
                            task = asyncio.create_task(wrapped_func)
                            tasks.append(task)
                            tasked_tool_ids.add(tc["id"])

    return tool_calls, tasks

async def main():
    prompt = "Take a quick 10 second power nap and dream about Telnyx. Then write a haiku about it!"
    messages = [{"role": "user", "content": prompt}]
    print(f"Prompt: {prompt}")

    functions = [sleep, dream]
    function_map = {f.__name__: f for f in functions}
    tools = [func_to_tool(func) for func in functions]

    chat_completion = await client.chat.completions.create(
        model=MODEL,
        messages=messages,
        tools=tools,
        tool_choice="required",
        stream=True
    )

    tool_calls, tasks = await handle_tool_calls(chat_completion, function_map)

    messages.append(
        {
            "role": "assistant",
            "tool_calls": tool_calls,
        }
    )

    task_results = await execute_tasks(tasks)
    messages.extend(task_results)

    print("Sending results back to LLM...")
    print()
    second_chat_completion = await client.chat.completions.create(
        model=MODEL,
        messages=messages,
        stream=True,
    )

    # GLM-5.2 is a reasoning model: stream reasoning_content (its thinking) and
    # content (the final answer) separately. Non-reasoning models omit the former.
    async for chunk in second_chat_completion:
        delta = chunk.choices[0].delta
        if getattr(delta, "reasoning_content", None):
            print(delta.reasoning_content, end="", flush=True)
        if delta.content:
            print(delta.content, end="", flush=True)
    print()

if __name__ == "__main__":
    asyncio.run(main())

Prompt: Take a quick 10 second power nap and dream about Telnyx. Then write a haiku about it!
Detected function: sleep
Executing sleep with {'seconds': 10}
Detected function: dream
Executing dream with {'subject': 'Telnyx'}
Executed dream, results: In my dream, I was walking through a futuristic cityscape where Telnyx's logo was emblazoned on skyscrapers, and I could hear the hum of millions of concurrent voice calls and messages being transmitted seamlessly through their network.
Executed sleep, results: I slept for 10 seconds!
Sending results back to LLM...

Here is a haiku about Telnyx:

Telnyx city glows
Voices whisper through the air
Connected we stand

message = chat_completion.choices[0].message
if getattr(message, "reasoning_content", None):
    print("reasoning:", message.reasoning_content)
print(message.content)  # the structured output

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("TELNYX_API_KEY"),
    base_url="https://api.telnyx.com/v2/ai/openai",
)

chat_completion = client.chat.completions.create(
    model="zai-org/GLM-5.2",
    messages=[
        {"role": "system", "content": "Classify the sentiment of this review as positive or negative."},
        {"role": "user", "content": "The staff went above and beyond! I had a great stay."}
    ],
    temperature=0.0,
    extra_body={
      "guided_choice": ["positive", "negative"]
    }
)
print(chat_completion.choices[0].message.content)

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("TELNYX_API_KEY"),
    base_url="https://api.telnyx.com/v2/ai/openai",
)

chat_completion = client.chat.completions.create(
    model="zai-org/GLM-5.2",
    messages=[
        {"role": "system", "content": "First describe the sentiment of the following review and then use that to classify the sentiment as positive or negative."},
        {"role": "user", "content": "The staff went above and beyond! I had a great stay."}
    ],
    temperature=0.0,
    extra_body={
      "guided_json": {
        "type": "object",
        "properties": {
          "sentiment": {
            "type": "string",
            "enum": ["positive", "negative"]
          },
          "explanation": {"type": "string"}
        },
        "required": ["sentiment", "explanation"]
      }
    }
)
print(chat_completion.choices[0].message.content)

{
  "sentiment": "positive",
  "explanation": "The review mentions that the staff went above and beyond and the user had a great stay, which indicates a positive sentiment."
}

import os
from enum import Enum
from openai import OpenAI
from pydantic import BaseModel

client = OpenAI(
    api_key=os.getenv("TELNYX_API_KEY"),
    base_url="https://api.telnyx.com/v2/ai/openai",
)

class Sentiment(str, Enum):
    positive = 'positive'
    negative = 'negative'

class SentimentAnalysis(BaseModel):
    explanation: str
    sentiment: Sentiment

chat_completion = client.chat.completions.create(
    model="zai-org/GLM-5.2",
    messages=[
        {"role": "system", "content": "First describe the sentiment of the following review and then use that to classify the sentiment as positive or negative."},
        {"role": "user", "content": "The staff went above and beyond! I had a great stay."}
    ],
    temperature=0.0,
    extra_body={
      "guided_json": SentimentAnalysis.model_json_schema()
    }
)
print(chat_completion.choices[0].message.content)

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("TELNYX_API_KEY"),
    base_url="https://api.telnyx.com/v2/ai/openai",
)

chat_completion = client.chat.completions.create(
    model="zai-org/GLM-5.2",
    messages=[
        {"role": "system", "content": "First describe the sentiment of the following review and then use that to classify the sentiment as positive or negative. Please respond using a JSON object."},
        {"role": "user", "content": "The staff went above and beyond! I had a great stay."}
    ],
    temperature=0.0,
    response_format={"type": "json_object"}
)
print(chat_completion.choices[0].message.content)

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("TELNYX_API_KEY"),
    base_url="https://api.telnyx.com/v2/ai/openai",
)

chat_completion = client.chat.completions.create(
    model="zai-org/GLM-5.2",
    messages=[
        {"role": "system", "content": "You are a concise and helpful AI assistant."},
        {"role": "user", "content": "Can you tell me about 10DLC?"}
    ],
    temperature=0.0,
    extra_body={
      "guided_regex": "(\\w+\\s*){1,20}[\.!?]"
    }
)
print(chat_completion.choices[0].message.content)

import os

from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("TELNYX_API_KEY"),
    base_url="https://api.telnyx.com/v2/ai/openai",
)

question = "<ADD QUESTION HERE>"
model = "<ADD FINE TUNED MODEL NAME HERE>"
chat_completion = client.chat.completions.create(
  messages=[
    {
        "role": "user",
        "content": question
    }
  ],
  model=model,
  stream=True
)

for chunk in chat_completion:
  if chunk.choices[0].delta.content:
    print(chunk.choices[0].delta.content, end="", flush=True)

import base64
import os

from openai import OpenAI
import requests

client = OpenAI(
    api_key=os.getenv("TELNYX_API_KEY"),
    base_url="https://api.telnyx.com/v2/ai/openai"
)

def encode_audio_base64_from_url(audio_url: str) -> str:
    """Encode audio retrieved from a remote url to base64 format."""
    with requests.get(audio_url) as response:
        response.raise_for_status()
        result = base64.b64encode(response.content).decode('utf-8')

    return f"data:audio/ogg;base64,{result}"

def process_audio(audio_url, instructions):
    chat_completion = client.chat.completions.create(
        model="fixie-ai/ultravox-v0_4_1-llama-3_1-8b",
        messages=[
            {
                "role": "system",
                "content": instructions
            },
            {
                "role": "user",
                "content": [
                    {
                        "type": "audio_url",
                        "audio_url": {
                            "url": audio_url,
                        },
                    },
                ],
            }
        ],
    )
    return chat_completion.choices[0].message.content

audio_url = "https://upload.wikimedia.org/wikipedia/commons/e/e0/Phrase_de_Neil_Armstrong.oga"
audio_base64 = encode_audio_base64_from_url(audio_url)

instructions = "Transcribe this verbatim. Do NOT respond with anything but the transcription."
print(f"Transcribe link: {process_audio(audio_url, instructions)}")
print(f"Transcribe base64: {process_audio(audio_base64, instructions)}")

instructions = "Translate this to French. Be faithful to the original while sounding like a native French speaker. Do NOT respond with anything but the translation."
print(f"Translate link: {process_audio(audio_url, instructions)}")

Transcribe link: That's one small step for man, one giant leap for mankind.
Transcribe base64: That's one small step for man, one giant leap for mankind.
Translate link: C'est un petit pas pour un homme, un grand pas pour l'humanité.