Audio & Transcription

Audio input capabilities enable models to chat and understand audio directly, this can be used for both chat use cases via audio or for optimal transcription purposes.

Models with Audio Capabilities

Audio capable models:

Voxtral Small (voxtral-small-latest) with audio input for chat use cases.
Voxtral Mini (voxtral-mini-latest) with audio input for chat use cases
And Voxtral Mini Transcribe (voxtral-mini-latest via audio/transcriptions), with an efficient transcription only service.

Chat with Audio

Our Voxtral models are capable of being used for chat use cases with our chat completions endpoint.

Passing an Audio File

To pass a local audio file, you can encode it in base64 and pass it as a string.

python
typescript
curl

import base64
from mistralai import Mistral

# Retrieve the API key from environment variables
api_key = os.environ["MISTRAL_API_KEY"]

# Specify model
model = "voxtral-mini-latest"

# Initialize the Mistral client
client = Mistral(api_key=api_key)

# Encode the audio file in base64
with open("examples/files/bcn_weather.mp3", "rb") as f:
    content = f.read()
audio_base64 = base64.b64encode(content).decode('utf-8')

# Get the chat response
chat_response = client.chat.complete(
    model=model,
    messages=[{
        "role": "user",
        "content": [
            {
                "type": "input_audio",
                "input_audio": audio_base64,
            },
            {
                "type": "text",
                "text": "What's in this file?"
            },
        ]
    }],
)

# Print the content of the response
print(chat_response.choices[0].message.content)

import { Mistral } from "@mistralai/mistralai";
import fs from "fs";

// Retrieve the API key from environment variables
const apiKey = process.env["MISTRAL_API_KEY"];

// Initialize the Mistral client
const client = new Mistral({ apiKey: apiKey });

// Encode the audio file in base64
const audio_file = fs.readFileSync('local_audio.mp3');
const audio_base64 = audio_file.toString('base64');

// Get the chat response
const chatResponse = await client.chat.complete({
  model: "voxtral-mini-latest",
  messages: [
    {
      role: "user",
      content: [
        {
          type: "input_audio",
          input_audio: audio_base64,
        },
        {
          type: "text",
          text: "What's in this file?",
        },
      ],
    },
  ],
});

// Print the content of the response
console.log(chatResponse.choices[0].message.content);

curl --location https://api.mistral.ai/v1/chat/completions \
  --header "Authorization: Bearer $MISTRAL_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "model": "voxtral-mini-latest",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "input_audio",
            "input_audio": "<audio_base64>",
          },
          {
            "type": "text",
            "text": "What'\''s in this file?"
          }
        ]
      }
    ]
  }'

Passing an Audio URL

You can also provide an url of a file.

python
typescript
curl

import os
from mistralai import Mistral

# Retrieve the API key from environment variables
api_key = os.environ["MISTRAL_API_KEY"]

# Specify model
model = "voxtral-mini-latest"

# Initialize the Mistral client
client = Mistral(api_key=api_key)

# Define the messages for the chat
messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "input_audio",
                "input_audio": "https://download.samplelib.com/mp3/sample-15s.mp3",
            },
            {
                "type": "text",
                "text": "What's in this file?"
            }
        ]
    }
]

# Get the chat response
chat_response = client.chat.complete(
    model=model,
    messages=messages
)

# Print the content of the response
print(chat_response.choices[0].message.content)

import { Mistral } from "@mistralai/mistralai";

// Retrieve the API key from environment variables
const apiKey = process.env["MISTRAL_API_KEY"];

// Initialize the Mistral client
const client = new Mistral({ apiKey: apiKey });

// Get the chat response
const chatResponse = await client.chat.complete({
  model: "voxtral-mini-latest",
  messages: [
    {
      role: "user",
      content: [
        {
          type: "input_audio",
          input_audio: "https://download.samplelib.com/mp3/sample-15s.mp3",
        },
        {
          type: "text",
          text: "What's in this file?",
        },
      ],
    },
  ],
});

// Print the content of the response
console.log("JSON:", chatResponse.choices[0].message.content);

curl --location https://api.mistral.ai/v1/chat/completions \
  --header "Authorization: Bearer $MISTRAL_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "model": "voxtral-mini-2507",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "input_audio",
            "input_audio": "https://download.samplelib.com/mp3/sample-15s.mp3"
          },
          {
            "type": "text",
            "text": "What'\''s in this file?"
          }
        ]
      }
    ]
  }'

Passing an Uploaded Audio File

Alternatively, you can upload a local file to our cloud and then use a signed URL for the task.

python
typescript
curl

import os
from mistralai import Mistral

# Retrieve the API key from environment variables
api_key = os.environ["MISTRAL_API_KEY"]

# Specify model
model = "voxtral-mini-latest"

# Initialize the Mistral client
client = Mistral(api_key=api_key)

# If local audio, upload and retrieve the signed url
with open("music.mp3", "rb") as f:
    uploaded_audio = client.files.upload(
      file={
          "content": f,
          "file_name": f.name
      },
      purpose="audio"
    )

signed_url = client.files.get_signed_url(file_id=uploaded_audio.id)

# Define the messages for the chat
messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "input_audio",
                "input_audio": signed_url.url,
            },
            {
                "type": "text",
                "text": "What's in this file?"
            }
        ]
    }
]

# Get the chat response
chat_response = client.chat.complete(
    model=model,
    messages=messages
)

# Print the content of the response
print(chat_response.choices[0].message.content)

import { Mistral } from "@mistralai/mistralai";
import fs from "fs";

const apiKey = process.env["MISTRAL_API_KEY"];

const client = new Mistral({ apiKey: apiKey });

// If local document, upload and retrieve the signed url
const audio_file = fs.readFileSync('local_audio.mp3');
const uploaded_audio = await client.files.upload({
  file: audio_file,
  purpose: "audio",
});
const signedUrl = await client.files.getSignedUrl({
    fileId: uploaded_audio.id,
});

// Get the chat response
const chatResponse = await client.chat.complete({
  model: "voxtral-mini-latest",
  messages: [
    {
      role: "user",
      content: [
        {
          type: "input_audio",
          input_audio: signedUrl.url,
        },
        {
          type: "text",
          text: "What's in this file?",
        },
      ],
    },
  ],
});

// Print the content of the response
console.log(chatResponse.choices[0].message.content);

Upload the Audio File

curl --location https://api.mistral.ai/v1/files \
  --header "Authorization: Bearer $MISTRAL_API_KEY" \
  --form purpose="audio" \
  --form file="@local_audio.mp3"

Get the Signed URL

curl --location "https://api.mistral.ai/v1/files/$id/url?expiry=24" \
    --header "Accept: application/json" \
    --header "Authorization: Bearer $MISTRAL_API_KEY"

Send Completion Request

curl --location https://api.mistral.ai/v1/chat/completions \
  --header "Authorization: Bearer $MISTRAL_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "model": "voxtral-mini-2507",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "input_audio",
            "input_audio": "<signed_url>"
          },
          {
            "type": "text",
            "text": "What'\''s in this file?"
          }
        ]
      }
    ]
  }'

Samples

Chat
Music
Compare Speakers

User

Assistant

Sure, here is the transcription of what you said:
"Today on July 15th, 2025, Mistral AI is announcing the new Voxtral models."
And here is the Python code to generate the first n digits of the Fibonacci sequence:

    def fibonacci(n):
if n <= 0:
    return []
elif n == 1:
    return [0]
elif n == 2:
    return [0, 1]

fib_sequence = [0, 1]
for i in range(2, n):
    next_value = fib_sequence[-1] + fib_sequence[-2]
    fib_sequence.append(next_value)

return fib_sequence

# Example usage:
n = 10  # Change this value to get the first n digits of the Fibonacci sequence
print(fibonacci(n))

This code defines a function fibonacci that takes an integer n and returns a list containing the first n digits of the Fibonacci sequence. You can change the value of n to get the desired number of Fibonacci digits.

Transcription

Transcription provides an optimized endpoint for transcription purposes and currently supports voxtral-mini-latest, which runs Voxtral Mini Transcribe.

Parameters
We provide different settings and parameters for transcription, such as:

timestamp_granularities: This allows you to set timestamps to track not only "what" was said but also "when". You can find more about timestamps here.
language: Our transcription service also works as a language detection service. However, you can manually set the language of the transcription for better accuracy if the language of the audio is already known.

Passing an Audio File

Among the different methods to pass the audio, you can directly provide a path to a file to upload and transcribe it as follows:

python
typescript
curl

import os
from mistralai import Mistral

# Retrieve the API key from environment variables
api_key = os.environ["MISTRAL_API_KEY"]

# Specify model
model = "voxtral-mini-latest"

# Initialize the Mistral client
client = Mistral(api_key=api_key)

# Get the transcription
with open("/path/to/file/audio.mp3", "rb") as f:
    transcription_response = client.audio.transcriptions.complete(
        model=model,
        file={
            "content": f,
            "file_name": "audio.mp3",
        },
        ## language="en"
    )

# Print the content of the response
print(transcription_response)

import { Mistral } from "@mistralai/mistralai";
import fs from "fs";

// Retrieve the API key from environment variables
const apiKey = process.env["MISTRAL_API_KEY"];

// Initialize the Mistral client
const client = new Mistral({ apiKey: apiKey });

// Get the transcription
const audio_file = fs.readFileSync('/path/to/file/audio.mp3');
const transcriptionResponse = await client.audio.transcriptions.complete({
  model: "voxtral-mini-latest",
  file: {
    fileName: "audio.mp3",
    content: audio_file,
  },
  // language: "en"
});

// Log the content of the response
console.log(transcriptionResponse);

curl --location 'https://api.mistral.ai/v1/audio/transcriptions' \
  --header "x-api-key: $MISTRAL_API_KEY" \
  --form 'file=@"/path/to/file/audio.mp3"' \
  --form 'model="voxtral-mini-2507"' \

With Language defined

curl --location 'https://api.mistral.ai/v1/audio/transcriptions' \
  --header "x-api-key: $MISTRAL_API_KEY" \
  --form 'file=@"/path/to/file/audio.mp3"' \
  --form 'model="voxtral-mini-2507"' \
  --form 'language="en"'

Passing an Audio URL

Similarly, you can provide an url of an audio file.

python
typescript
curl

import os
from mistralai import Mistral

# Retrieve the API key from environment variables
api_key = os.environ["MISTRAL_API_KEY"]

# Specify model
model = "voxtral-mini-latest"

# Initialize the Mistral client
client = Mistral(api_key=api_key)

# Get the transcription
transcription_response = client.audio.transcriptions.complete(
    model=model,
    file_url="https://docs.mistral.ai/audio/obama.mp3",
    ## language="en"
)

# Print the content of the response
print(transcription_response)

import { Mistral } from "@mistralai/mistralai";

// Retrieve the API key from environment variables
const apiKey = process.env["MISTRAL_API_KEY"];

// Initialize the Mistral client
const client = new Mistral({ apiKey: apiKey });

// Get the transcription
const transcriptionResponse = await client.audio.transcriptions.complete({
  model: "voxtral-mini-latest",
  fileUrl: "https://docs.mistral.ai/audio/obama.mp3",
  // language: "en"
});

// Log the content of the response
console.log(transcriptionResponse);

curl --location 'https://api.mistral.ai/v1/audio/transcriptions' \
  --header "x-api-key: $MISTRAL_API_KEY" \
  --form 'file_url="https://docs.mistral.ai/audio/obama.mp3"' \
  --form 'model="voxtral-mini-2507"'

With Language defined

curl --location 'https://api.mistral.ai/v1/audio/transcriptions' \
  --header "x-api-key: $MISTRAL_API_KEY" \
  --form 'file_url="https://docs.mistral.ai/audio/obama.mp3"' \
  --form 'model="voxtral-mini-2507"' \
  --form 'language="en"'

Passing an Uploaded Audio File

Alternatively, you can first upload the file to our cloud service and then pass the signed URL instead.

python
typescript
curl

import os
from mistralai import Mistral

# Retrieve the API key from environment variables
api_key = os.environ["MISTRAL_API_KEY"]

# Specify model
model = "voxtral-mini-latest"

# Initialize the Mistral client
client = Mistral(api_key=api_key)

# If local audio, upload and retrieve the signed url
with open("local_audio.mp3", "rb") as f:
    uploaded_audio = client.files.upload(
        file={
            "content": f,
            "file_name": "local_audio.mp3",
            },
        purpose="audio"
    )

signed_url = client.files.get_signed_url(file_id=uploaded_audio.id)

# Get the transcription
transcription_response = client.audio.transcriptions.complete(
    model=model,
    file_url=signed_url.url,
    ## language="en"
)

# Print the content of the response
print(transcription_response)

import { Mistral } from "@mistralai/mistralai";
import fs from "fs";

// Retrieve the API key from environment variables
const apiKey = process.env["MISTRAL_API_KEY"];

// Initialize the Mistral client
const client = new Mistral({ apiKey: apiKey });

// If local document, upload and retrieve the signed url
const uploaded_pdf = await client.files.upload({
    file: {
        fileName: "local_audio.mp3",
        content: fs.readFileSync("local_audio.mp3"),
        },
    purpose: "audio",
});

const signedUrl = await client.files.getSignedUrl({
    fileId: uploaded_pdf.id,
});

// Get the transcription
const transcriptionResponse = await client.audio.transcriptions.complete({
    model: "voxtral-mini-latest",
    fileUrl: signedUrl.url,
    // language: "en"
});

// Log the content of the response
console.log(transcriptionResponse);

Upload the Audio File

curl --location https://api.mistral.ai/v1/files \
  --header "Authorization: Bearer $MISTRAL_API_KEY" \
  --form purpose="audio" \
  --form file="@local_audio.mp3"

Get the Signed URL

curl --location "https://api.mistral.ai/v1/files/$id/url?expiry=24" \
    --header "Accept: application/json" \
    --header "Authorization: Bearer $MISTRAL_API_KEY"

Send Transcription Request

curl --location 'https://api.mistral.ai/v1/audio/transcriptions' \
    --header "x-api-key: $MISTRAL_API_KEY" \
    --form 'file_url="<signed_url>"' \
    --form 'model="voxtral-mini-2507"'

Send Transcription Request with Language defined

curl --location 'https://api.mistral.ai/v1/audio/transcriptions' \
    --header "x-api-key: $MISTRAL_API_KEY" \
    --form 'file_url="<signed_url>"' \
    --form 'model="voxtral-mini-2507"' \
    --form 'language="en"'

JSON Output

{
  "model":"voxtral-mini-2507",
  "text":"This week, I traveled to Chicago to deliver my final farewell address to the nation, following in the tradition of presidents before me. It was an opportunity to say thank you. Whether we've seen eye to eye or rarely agreed at all, my conversations with you, the American people, in living rooms, in schools, at farms and on factory floors, at diners and on distant military outposts, All these conversations are what have kept me honest, kept me inspired, and kept me going. Every day, I learned from you. You made me a better President, and you made me a better man. Over the course of these eight years, I've seen the goodness, the resilience, and the hope of the American people. I've seen neighbors looking out for each other as we rescued our economy from the worst crisis of our lifetimes. I've hugged cancer survivors who finally know the security of affordable health care. I've seen communities like Joplin rebuild from disaster, and cities like Boston show the world that no terrorist will ever break the American spirit. I've seen the hopeful faces of young graduates and our newest military officers. I've mourned with grieving families searching for answers. And I found grace in a Charleston church. I've seen our scientists help a paralyzed man regain his sense of touch, and our wounded warriors walk again. I've seen our doctors and volunteers rebuild after earthquakes and stop pandemics in their tracks. I've learned from students who are building robots and curing diseases, and who will change the world in ways we can't even imagine. I've seen the youngest of children remind us of our obligations to care for our refugees. to work in peace, and above all, to look out for each other. That's what's possible when we come together in the slow, hard, sometimes frustrating, but always vital work of self-government. But we can't take our democracy for granted. All of us, regardless of party, should throw ourselves into the work of citizenship. Not just when there is an election. Not just when our own narrow interest is at stake. But over the full span of a lifetime. If you're tired of arguing with strangers on the Internet, try to talk with one in real life. If something needs fixing, lace up your shoes and do some organizing. If you're disappointed by your elected officials, then grab a clipboard, get some signatures, and run for office yourself. Our success depends on our participation, regardless of which way the pendulum of power swings. It falls on each of us to be guardians of our democracy. to embrace the joyous task we've been given to continually try to improve this great nation of ours. Because for all our outward differences, we all share the same proud title – citizen. It has been the honor of my life to serve you as President. Eight years later, I am even more optimistic about our country's promise. And I look forward to working along your side as a citizen for all my days that remain. Thanks, everybody. God bless you. And God bless the United States of America.",
  "language":"en",
  "segments":[],
  "usage":{
    "prompt_audio_seconds":203,
    "prompt_tokens":4,
    "total_tokens":3264,
    "completion_tokens":635
  }
}

Samples

Obama

Audio

Transcription
This week, I traveled to Chicago to deliver my final farewell address to the nation, following in the tradition of presidents before me. It was an opportunity to say thank you. Whether we've seen eye to eye or rarely agreed at all, my conversations with you, the American people, in living rooms, in schools, at farms and on factory floors, at diners and on distant military outposts, All these conversations are what have kept me honest, kept me inspired, and kept me going. Every day, I learned from you. You made me a better President, and you made me a better man. Over the course of these eight years, I've seen the goodness, the resilience, and the hope of the American people. I've seen neighbors looking out for each other as we rescued our economy from the worst crisis of our lifetimes. I've hugged cancer survivors who finally know the security of affordable health care. I've seen communities like Joplin rebuild from disaster, and cities like Boston show the world that no terrorist will ever break the American spirit. I've seen the hopeful faces of young graduates and our newest military officers. I've mourned with grieving families searching for answers. And I found grace in a Charleston church. I've seen our scientists help a paralyzed man regain his sense of touch, and our wounded warriors walk again. I've seen our doctors and volunteers rebuild after earthquakes and stop pandemics in their tracks. I've learned from students who are building robots and curing diseases, and who will change the world in ways we can't even imagine. I've seen the youngest of children remind us of our obligations to care for our refugees. to work in peace, and above all, to look out for each other. That's what's possible when we come together in the slow, hard, sometimes frustrating, but always vital work of self-government. But we can't take our democracy for granted. All of us, regardless of party, should throw ourselves into the work of citizenship. Not just when there is an election. Not just when our own narrow interest is at stake. But over the full span of a lifetime. If you're tired of arguing with strangers on the Internet, try to talk with one in real life. If something needs fixing, lace up your shoes and do some organizing. If you're disappointed by your elected officials, then grab a clipboard, get some signatures, and run for office yourself. Our success depends on our participation, regardless of which way the pendulum of power swings. It falls on each of us to be guardians of our democracy. to embrace the joyous task we've been given to continually try to improve this great nation of ours. Because for all our outward differences, we all share the same proud title – citizen. It has been the honor of my life to serve you as President. Eight years later, I am even more optimistic about our country's promise. And I look forward to working along your side as a citizen for all my days that remain. Thanks, everybody. God bless you. And God bless the United States of America.

Language English

Transcription with Timestamps

You can request timestamps for the transcription by passing the timestamp_granularities parameter, currently supporting segment.
It will return the start and end time of each segment in the audio file.

python
typescript
curl

import os
from mistralai import Mistral

# Retrieve the API key from environment variables
api_key = os.environ["MISTRAL_API_KEY"]

# Specify model
model = "voxtral-mini-latest"

# Initialize the Mistral client
client = Mistral(api_key=api_key)

# Transcribe the audio with timestamps
transcription_response = client.audio.transcriptions.complete(
    model=model,
    file_url="https://docs.mistral.ai/audio/obama.mp3",
    timestamp_granularities="segment"
)

# Print the contents
print(transcription_response)

import { Mistral } from "@mistralai/mistralai";

// Retrieve the API key from environment variables
const apiKey = process.env["MISTRAL_API_KEY"];

// Initialize the Mistral client
const client = new Mistral({ apiKey: apiKey });

// Transcribe the audio with timestamps
const transcriptionResponse = await client.audio.transcriptions.complete({
  model: "voxtral-mini-latest",
  fileUrl: "https://docs.mistral.ai/audio/obama.mp3",
  timestamp_granularities: "segment"
});

// Log the contents
console.log(transcriptionResponse);

curl --location 'https://api.mistral.ai/v1/audio/transcriptions' \
--header "x-api-key: $MISTRAL_API_KEY" \
--form 'file_url="https://docs.mistral.ai/audio/obama.mp3"' \
--form 'model="voxtral-mini-latest"'
--form 'timestamp_granularities="segment"'

JSON Output

{
  "model": "voxtral-mini-2507",
  "text": "This week, I traveled to Chicago to deliver my final farewell address to the nation, following in the tradition of presidents before me. It was an opportunity to say thank you. Whether we've seen eye to eye or rarely agreed at all, my conversations with you, the American people, in living rooms, in schools, at farms and on factory floors, at diners and on distant military outposts. All these conversations are what have kept me honest, kept me inspired, and kept me going. Every day, I learned from you. You made me a better President, and you made me a better man. Over the course of these eight years, I've seen the goodness, the resilience, and the hope of the American people. I've seen neighbors looking out for each other as we rescued our economy from the worst crisis of our lifetimes. I've hugged cancer survivors who finally know the security of affordable health care. I've seen communities like Joplin rebuild from disaster, and cities like Boston show the world that no terrorist will ever break the American spirit. I've seen the hopeful faces of young graduates and our newest military officers. I've mourned with grieving families searching for answers. And I found grace in a Charleston church. I've seen our scientists help a paralyzed man regain his sense of touch and our wounded warriors walk again. I've seen our doctors and volunteers rebuild after earthquakes and stop pandemics in their tracks. I've learned from students who are building robots and curing diseases and who will change the world in ways we can't even imagine. I've seen the youngest of children remind us of our obligations to care for our refugees. to work in peace, and above all, to look out for each other. That's what's possible when we come together in the slow, hard, sometimes frustrating, but always vital work of self-government. But we can't take our democracy for granted. All of us, regardless of party, should throw ourselves into the work of citizenship. Not just when there's an election. Not just when our own narrow interest is at stake. But over the full span of a lifetime. If you're tired of arguing with strangers on the Internet, try to talk with one in real life. If something needs fixing, lace up your shoes and do some organizing. If you're disappointed by your elected officials, then grab a clipboard, get some signatures, and run for office yourself. Our success depends on our participation, regardless of which way the pendulum of power swings. It falls on each of us to be guardians of our democracy. to embrace the joyous task we've been given to continually try to improve this great nation of ours. Because for all our outward differences, we all share the same proud title, citizen. It has been the honor of my life to serve you as president. Eight years later, I am even more optimistic about our country's promise, and I look forward to working along your side as a citizen for all my days that remain. Thanks, everybody. God bless you, and God bless the United States of America.",
  "language": null,
  "segments": [
    {
      "text": "This week, I traveled to Chicago to deliver my final farewell address to the nation, following",
      "start": 0.8,
      "end": 6.2
    },
    {
      "text": "in the tradition of presidents before me.",
      "start": 6.2,
      "end": 9.0
    },
    {
      "text": "It was an opportunity to say thank you.",
      "start": 9.0,
      "end": 11.8
    },
    {
      "text": "Whether we've seen eye to eye or rarely agreed at all, my conversations with you, the American",
      "start": 11.8,
      "end": 17.6
    },
    {
      "text": "people, in living rooms, in schools, at farms and on factory floors, at diners and on distant",
      "start": 17.6,
      "end": 24.9
    },
    {
      "text": "military outposts.",
      "start": 24.9,
      "end": 26.6
    },
    {
      "text": "All these conversations are what have kept me honest, kept me inspired, and kept me going.",
      "start": 26.6,
      "end": 32.8
    },
    {
      "text": "Every day, I learned from you.",
      "start": 32.8,
      "end": 35.4
    },
    {
      "text": "You made me a better President, and you made me a better man.",
      "start": 35.4,
      "end": 39.3
    },
    {
      "text": "Over the course of these eight years, I've seen the goodness, the resilience, and the hope of the American people.",
      "start": 39.3,
      "end": 46.1
    },
    {
      "text": "I've seen neighbors looking out for each other as we rescued our economy from the worst crisis of our lifetimes.",
      "start": 46.1,
      "end": 51.3
    },
    {
      "text": "I've hugged cancer survivors who finally know the security of affordable health care.",
      "start": 52.2,
      "end": 56.5
    },
    {
      "text": "I've seen communities like Joplin rebuild from disaster, and cities like Boston show the world that no terrorist will ever break the American spirit.",
      "start": 57.1,
      "end": 65.7
    },
    {
      "text": "I've seen the hopeful faces of young graduates and our newest military officers.",
      "start": 66.5,
      "end": 71.1
    },
    {
      "text": "I've mourned with grieving families searching for answers.",
      "start": 71.7,
      "end": 74.4
    },
    {
      "text": "And I found grace in a Charleston church.",
      "start": 75.2,
      "end": 77.7
    },
    {
      "text": "I've seen our scientists help a paralyzed man regain his sense of touch and our wounded warriors walk again.",
      "start": 78.5,
      "end": 85.2
    },
    {
      "text": "I've seen our doctors and volunteers rebuild after earthquakes and stop pandemics in their tracks.",
      "start": 85.9,
      "end": 91.9
    },
    {
      "text": "I've learned from students who are building robots and curing diseases and who will change the world in ways we can't even imagine.",
      "start": 92.6,
      "end": 99.2
    },
    {
      "text": "I've seen the youngest of children remind us of our obligations to care for our refugees.",
      "start": 100.1,
      "end": 105.8
    },
    {
      "text": "to work in peace, and above all, to look out for each other.",
      "start": 106.6,
      "end": 111.6
    },
    {
      "text": "That's what's possible when we come together in the slow, hard, sometimes frustrating, but always vital work of self-government.",
      "start": 111.6,
      "end": 120.3
    },
    {
      "text": "But we can't take our democracy for granted.",
      "start": 120.3,
      "end": 123.4
    },
    {
      "text": "All of us, regardless of party, should throw ourselves into the work of citizenship.",
      "start": 123.4,
      "end": 129.2
    },
    {
      "text": "Not just when there's an election.",
      "start": 129.2,
      "end": 131.2
    },
    {
      "text": "Not just when our own narrow interest is at stake.",
      "start": 131.2,
      "end": 134.7
    },
    {
      "text": "But over the full span of a lifetime.",
      "start": 134.7,
      "end": 138.1
    },
    {
      "text": "If you're tired of arguing with strangers on the Internet,",
      "start": 138.1,
      "end": 141.4
    },
    {
      "text": "try to talk with one in real life.",
      "start": 141.4,
      "end": 144.0
    },
    {
      "text": "If something needs fixing,",
      "start": 144.0,
      "end": 146.0
    },
    {
      "text": "lace up your shoes and do some organizing.",
      "start": 146.0,
      "end": 149.3
    },
    {
      "text": "If you're disappointed by your elected officials, then grab a clipboard, get some signatures, and run for office yourself.",
      "start": 149.3,
      "end": 156.8
    },
    {
      "text": "Our success depends on our participation, regardless of which way the pendulum of power swings.",
      "start": 156.8,
      "end": 165.3
    },
    {
      "text": "It falls on each of us to be guardians of our democracy.",
      "start": 165.3,
      "end": 168.5
    },
    {
      "text": "to embrace the joyous task we've been given to continually try to improve this great nation of ours.",
      "start": 168.5,
      "end": 174.6
    },
    {
      "text": "Because for all our outward differences, we all share the same proud title, citizen.",
      "start": 175.4,
      "end": 181.7
    },
    {
      "text": "It has been the honor of my life to serve you as president.",
      "start": 182.7,
      "end": 186.0
    },
    {
      "text": "Eight years later, I am even more optimistic about our country's promise,",
      "start": 186.9,
      "end": 190.3
    },
    {
      "text": "and I look forward to working along your side as a citizen for all my days that remain.",
      "start": 190.3,
      "end": 197.3
    },
    {
      "text": "Thanks, everybody. God bless you, and God bless the United States of America.",
      "start": 198.5,
      "end": 203.4
    }
  ],
  "usage": {
    "prompt_audio_seconds": 203,
    "prompt_tokens": 4,
    "total_tokens": 3945,
    "completion_tokens": 1316
  }
}

FAQ

What's the maximum audio length?

The maximum length will depend on the endpoint used, currently the limits are as follows:
- ≈20 minutes for Chat with Audio for both models.
- ≈15 minutes for Transcription, longer transcriptions will be available soon.

tip

Here are some tips if you need to handle longer audio files:

Divide the audio into smaller segments: Transcribe each segment individually. However, be aware that this might lead to a loss of context, difficulties in splitting the audio at natural pauses (such as mid-sentence), and the need to combine the transcriptions afterward.
Increase the playback speed: Send the file at a faster pace by speeding up the audio. Keep in mind that this can reduce audio quality and require adjusting the transcription timestamps to align with the original audio file.

Models with Audio Capabilities​

Chat with Audio​

Passing an Audio File​

Passing an Audio URL​

Passing an Uploaded Audio File​

Transcription​

Passing an Audio File​

Passing an Audio URL​

Passing an Uploaded Audio File​

Transcription with Timestamps​

FAQ​

Models with Audio Capabilities

Chat with Audio

Passing an Audio File

Passing an Audio URL

Passing an Uploaded Audio File

Transcription

Passing an Audio File

Passing an Audio URL

Passing an Uploaded Audio File

Transcription with Timestamps

FAQ