Name: IBM Granite Speech 4.1 2B Speech Recognition API
Brand: magicapi
SKU: api-magicapi-multilingual-speech-translation-api-ibm-granite-granite-speech-4-1-2b
Availability: InStock
Author: API Market

Shashank Agarwal

# 🎙️ Speech Recognition and Translation API (IBM Granite Speech 4.1 2B)

## Overview
Granite Speech 4.1 2B is a speech-language model from IBM. Its developer describes it as a compact and efficient model designed for multilingual automatic speech recognition (ASR) and bidirectional automatic speech translation (AST) for English, French, German, Spanish, Portuguese and Japanese.

Send one or more `audio` URLs together with a text `prompt` that says what to do, for example "Transcribe the speech with proper punctuation and capitalization." Instead of `prompt` you can send a chat `messages` list. The model answers in text. The output is a list of text chunks; join them to get the full answer.

## Features
- **Speech recognition**: transcribe spoken audio into text with a prompt such as "Transcribe the speech with proper punctuation and capitalization."
- **Speech translation**: its developer describes the model as built for bidirectional speech translation across the supported languages; ask for the translation in the `prompt`.
- **Audio list**: `audio` takes an array of audio file URLs.
- **Prompt or chat messages**: send a single `prompt` or a `messages` list, with an optional `system_prompt`, `chat_template`, `chat_template_kwargs` and `add_generation_prompt`.
- **Generation controls**: `max_completion_tokens`, `min_tokens`, `temperature`, `top_p`, `top_k`, `presence_penalty`, `frequency_penalty`, `repetition_penalty`, `stop` and `seed`.
- **Low input price**: an input token is billed at 0.12 of an output token.

## Use Cases
1. **Transcripts**: turn recorded speech into punctuated written text.
2. **Speech translation**: get the text of a recording in another supported language.
3. **Voice notes to text**: convert short voice messages into text for search, tickets or CRM notes.
4. **Captions**: produce the text of a clip as a starting point for captions.

## Visual Examples
### Example Input
[Listen to the example input audio](https://blog.api.market/wp-content/uploads/2026/10/granite-speech-3-3-8b-input-api-market.wav)

Prompt: "Transcribe the speech with proper punctuation and capitalization."

Settings: `temperature` 0.2, `top_p` 0.9, `top_k` 50, `min_tokens` 0, `add_generation_prompt` `true`, `stream` `false`; `stop`, `messages` and `chat_template_kwargs` sent empty.

### Example Output
The model returned a list with one text chunk:

> After his nap, Timothy lazily stretched, first one gray velvet foot, then another, strolled indolently to his plate, turning over the food, carefully selecting choice bits, nosing out that which he scorned upon the clean hearth

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | No | none |  | User prompt, for example "Transcribe the speech with proper punctuation and capitalization." |
| `messages` | array of objects | No | none |  | Chat completion messages (a list of message objects), as an alternative to `prompt`. |
| `audio` | array of strings (URLs) | No | none |  | Audio file URLs for the model to process. |
| `system_prompt` | string | No | none |  | System prompt. The chat template provides a good default. |
| `chat_template` | string | No | none |  | A template to format the prompt with. If not set, the model's own chat template is used. |
| `add_generation_prompt` | boolean | No | `true` |  | Add the generation prompt. Passed to the chat template. |
| `chat_template_kwargs` | object | No | none |  | Additional arguments passed to the chat template. |
| `min_tokens` | integer | No | `0` |  | The minimum number of tokens the model should generate. |
| `max_tokens` | integer | No | none |  | Deprecated in favor of `max_completion_tokens`. |
| `max_completion_tokens` | integer | No | none |  | Upper bound for the number of tokens generated for a completion, including visible output tokens and reasoning tokens. |
| `temperature` | number | No | none |  | The value used to modulate the next token probabilities. |
| `top_p` | number | No | none |  | Probability threshold. If below 1.0, only the top tokens with cumulative probability at or above `top_p` are kept (nucleus filtering). |
| `top_k` | integer | No | none |  | Number of highest probability tokens to consider. If above 0, only the top k tokens are kept (top-k filtering). |
| `presence_penalty` | number | No | none |  | Presence penalty. |
| `frequency_penalty` | number | No | none |  | Frequency penalty. |
| `repetition_penalty` | number | No | none |  | Repetition penalty. |
| `stop` | array of strings | No | none |  | Sequences to stop generation at. For example, `["<end>", "<stop>"]` stops generation at the first `<end>` or `<stop>`. |
| `seed` | integer | No | none |  | Random seed. Leave unset to randomize the seed. |
| `stream` | boolean | No | none |  | Request a streaming response. The example sends `false` and reads the result by polling. |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.0032 per API unit.
- **1 API unit = 10,000 weighted tokens; an output token counts 1, an input token counts 0.12.** Each request is rounded up to a whole unit.
- **Per million tokens**: input tokens $0.0384, output tokens $0.32. Input tokens cover the prompt and the audio.
- **Example cost**: the example request used 190 input tokens and 51 output tokens: 190 x 0.12 + 51 = 73.8 weighted tokens, rounded up to 1 unit ($0.0032).
- **Failed or cancelled predictions are not billed.**
- **GET requests to check prediction status** are free and don't count toward API unit usage.
- **No monthly subscription fee.**

## API Documentation

### Base URL
All API requests go to: `https://prod.api.market/api/v1/magicapi/multilingual-speech-translation-api-ibm-granite-granite-speech-4-1-2b`

### Authentication
Send your api.market API key in the `x-api-market-key` header:
```
x-api-market-key: YOUR_API_MARKET_KEY
```

### Asynchronous Processing
**IMPORTANT**: This API is asynchronous. The flow is:
1. Send a POST request to `/predictions`. A successful request returns **201 Created** with a prediction `id` and a `status` of `starting` or `processing`.
2. Poll GET `/predictions/{id}` with that ID.
3. Keep polling while `status` is `starting` or `processing`.
4. Stop when `status` is `succeeded` (read `output`), `failed` or `canceled` (read `error`).

A polling interval of 1 second and an overall timeout of 600 seconds (10 minutes) work well.

### Endpoints

#### Create a Prediction
```bash
curl -X POST "https://prod.api.market/api/v1/magicapi/multilingual-speech-translation-api-ibm-granite-granite-speech-4-1-2b/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "25d7a190df066d4623579c05619cafb1eeff766ee0bdce4d8b7c82726ca93e58",
    "input": {
      "stop": [],
      "audio": [
        "https://blog.api.market/wp-content/uploads/2026/10/granite-speech-3-3-8b-input-api-market.wav"
      ],
      "top_k": 50,
      "top_p": 0.9,
      "prompt": "Transcribe the speech with proper punctuation and capitalization.",
      "stream": false,
      "messages": [],
      "min_tokens": 0,
      "temperature": 0.2,
      "chat_template_kwargs": {},
      "add_generation_prompt": true
    }
  }'
```

Response (201 Created):
```json
{
  "id": "v91fe1yhhdrmt0d1f1g9exfemc",
  "version": "25d7a190df066d4623579c05619cafb1eeff766ee0bdce4d8b7c82726ca93e58",
  "status": "starting",
  "created_at": "2026-10-26T13:22:53.594Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/multilingual-speech-translation-api-ibm-granite-granite-speech-4-1-2b/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "v91fe1yhhdrmt0d1f1g9exfemc",
  "status": "succeeded",
  "output": [
    "After his nap, Timothy lazily stretched, first one gray velvet foot, then another, strolled indolently to his plate, turning over the food, carefully selecting choice bits, nosing out that which he scorned upon the clean hearth"
  ],
  "error": null,
  "created_at": "2026-10-26T13:22:53.594Z",
  "started_at": "2026-10-26T13:24:34.275Z",
  "completed_at": "2026-10-26T13:24:35.841Z"
}
```

`output` is an array of text chunks. Join them without a separator to get the full answer.

### Status Codes
- **201 Created**: prediction created (POST `/predictions`). This is the normal success response.
- **200 OK**: prediction details returned (GET `/predictions/{id}`).
- **400 Bad Request**: invalid input, for example `audio` that is not an array of URLs.
- **401 Unauthorized**: missing or invalid API key.
- **404 Not Found**: no prediction with that ID.
- **429 Too Many Requests**: rate limit exceeded.
- **500 Internal Server Error** or **503 Service Unavailable**: temporary server problem; retry later.

## Rate Limits
Requests are rate limited to keep usage fair. If you receive a 429 response, wait and retry with exponential backoff.

## Error Handling
- Check the HTTP status code of every request and read the response body for the error message.
- A prediction can also end with `status` set to `failed`; the `error` field then explains why. Failed predictions are not billed.
- Retry 429, 500 and 503 responses with exponential backoff. Fix the input before retrying a 400.

## Implementation Guide
### Example Code

#### JavaScript
```javascript
const apiKey = "YOUR_API_MARKET_KEY";
const baseUrl = "https://prod.api.market/api/v1/magicapi/multilingual-speech-translation-api-ibm-granite-granite-speech-4-1-2b";

async function createAndWaitForPrediction(input) {
  const response = await fetch(`${baseUrl}/predictions`, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "x-api-market-key": apiKey
    },
    body: JSON.stringify({ version: "25d7a190df066d4623579c05619cafb1eeff766ee0bdce4d8b7c82726ca93e58", input })
  });

  if (response.status !== 201) {
    throw new Error(`API error: ${response.status} ${await response.text()}`);
  }

  const prediction = await response.json();
  return pollForResults(prediction.id);
}

const delay = (ms) => new Promise((resolve) => setTimeout(resolve, ms));

async function pollForResults(predictionId) {
  const maxTimeout = 600000;
  const pollInterval = 1000;
  const startTime = Date.now();

  while (Date.now() - startTime < maxTimeout) {
    const response = await fetch(`${baseUrl}/predictions/${predictionId}`, {
      headers: { "x-api-market-key": apiKey }
    });

    if (!response.ok) {
      throw new Error(`API error: ${response.status} ${await response.text()}`);
    }

    const prediction = await response.json();

    if (prediction.status === "succeeded") {
      return prediction.output.join("");
    }

    if (prediction.status === "failed" || prediction.status === "canceled") {
      throw new Error(`Prediction ${prediction.status}: ${prediction.error || "Unknown error"}`);
    }

    await delay(pollInterval);
  }

  throw new Error("Prediction timed out after 10 minutes");
}

createAndWaitForPrediction({
  "stop": [],
  "audio": [
    "https://blog.api.market/wp-content/uploads/2026/10/granite-speech-3-3-8b-input-api-market.wav"
  ],
  "top_k": 50,
  "top_p": 0.9,
  "prompt": "Transcribe the speech with proper punctuation and capitalization.",
  "stream": false,
  "messages": [],
  "min_tokens": 0,
  "temperature": 0.2,
  "chat_template_kwargs": {},
  "add_generation_prompt": true
}).then((output) => console.log(output));
```

#### Python
```python
import time
import requests

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/multilingual-speech-translation-api-ibm-granite-granite-speech-4-1-2b"


def create_and_wait_for_prediction(input_data):
    headers = {"Content-Type": "application/json", "x-api-market-key": API_KEY}
    response = requests.post(
        f"{BASE_URL}/predictions",
        headers=headers,
        json={"version": "25d7a190df066d4623579c05619cafb1eeff766ee0bdce4d8b7c82726ca93e58", "input": input_data},
    )

    if response.status_code != 201:
        raise Exception(f"API error: {response.status_code} {response.text}")

    return poll_for_results(response.json()["id"])


def poll_for_results(prediction_id):
    max_timeout = 600
    poll_interval = 1
    headers = {"x-api-market-key": API_KEY}
    start_time = time.time()

    while time.time() - start_time < max_timeout:
        response = requests.get(f"{BASE_URL}/predictions/{prediction_id}", headers=headers)

        if response.status_code != 200:
            raise Exception(f"API error: {response.status_code} {response.text}")

        prediction = response.json()

        if prediction["status"] == "succeeded":
            return "".join(prediction["output"])

        if prediction["status"] in ("failed", "canceled"):
            raise Exception(f"Prediction {prediction['status']}: {prediction.get('error') or 'Unknown error'}")

        time.sleep(poll_interval)

    raise Exception("Prediction timed out after 10 minutes")


print(create_and_wait_for_prediction({
    "stop": [],
    "audio": [
        "https://blog.api.market/wp-content/uploads/2026/10/granite-speech-3-3-8b-input-api-market.wav"
    ],
    "top_k": 50,
    "top_p": 0.9,
    "prompt": "Transcribe the speech with proper punctuation and capitalization.",
    "stream": False,
    "messages": [],
    "min_tokens": 0,
    "temperature": 0.2,
    "chat_template_kwargs": {},
    "add_generation_prompt": True
}))
```

## FAQ
- **How do I tell the model what to do with the audio?**
  - Put the instruction in `prompt`, for example "Transcribe the speech with proper punctuation and capitalization." The audio goes in `audio` as an array of URLs.
- **Which languages are supported?**
  - Its developer lists English, French, German, Spanish, Portuguese and Japanese for speech recognition and bidirectional speech translation.
- **Why is the output a list?**
  - The model returns its answer as text chunks. Join them without a separator to get the full text.
- **What am I billed for?**
  - Weighted tokens: $0.32 per million output tokens and $0.0384 per million input tokens, in units of 10,000 weighted tokens ($0.0032), rounded up per request.
- **Is the 201 response from POST an error?**
  - No. 201 Created means the prediction was accepted. Use the returned `id` to poll GET `/predictions/{id}` until `status` is `succeeded`, `failed` or `canceled`.
- **What if my prediction fails?**
  - Failed predictions are not billed. Read the `error` field, check that the audio URL is reachable and try again.

## Contact Us
If you have any questions or need assistance, you can reach out to us through the embedded chat on the bottom right corner of the page or send an email to hello@magicapi.com.


Transcribe and translate speech in English, French, German, Spanish, Portuguese and Japanese with IBM Granite Speech 4.1 2B, pay as you go.