Skip to content
StatusStart free

Speech & audio

MirAPI has three OpenAI-compatible audio endpoints: transcription turns speech into text, translation turns audio into English, and text-to-speech generates speech from text. All three use the OpenAI protocol, so you authenticate with Authorization: Bearer and point your OpenAI SDK at https://api.mirapi.ai/v1.

Endpoint What it does Request Response
POST /v1/audio/transcriptions Transcribe audio to text multipart/form-data JSON with a text field
POST /v1/audio/translations Translate audio to English multipart/form-data JSON with a text field
POST /v1/audio/speech Synthesize speech from text JSON body Raw audio bytes

Transcribing and translating

Section titled “Transcribing and translating”

Both endpoints take the audio file as multipart/form-data; file and model are required. transcriptions returns the text in the language of the audio (or the one you set with language), while translations always returns English.

Uploading a file

Section titled “Uploading a file”
Terminal window
curl https://api.mirapi.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $MIRAPI_API_KEY" \
  -F file=@speech.mp3 \
  -F model="deepseek-chat" \
  -F response_format="json"
import os
from openai import OpenAI


client = OpenAI(base_url="https://api.mirapi.ai/v1", api_key=os.environ["MIRAPI_API_KEY"])


with open("speech.mp3", "rb") as audio:
    transcript = client.audio.transcriptions.create(
        model="deepseek-chat",
        file=audio,
        response_format="json",
    )


print(transcript.text)

For translation, change the path to /v1/audio/translations. The request shape is the same.

Parameters

Section titled “Parameters”
Field Type Required Notes
file binary Yes The audio file
model string Yes Speech-to-text model name from the catalog
language string No ISO-639-1 language code (transcriptions only)
prompt string No Context or terminology hint to steer the transcript
response_format string No json (default), text, srt, verbose_json, vtt
temperature number No Sampling temperature
timestamp_granularities array No word and/or segment (transcriptions only)

translations accepts the same fields except language and timestamp_granularities.

Response formats

Section titled “Response formats”

response_format controls the shape of the result:

  • json (default): a JSON object with a text field.
  • text: the transcript as plain text.
  • srt and vtt: subtitle files.
  • verbose_json: a JSON object with segment-level detail. Add timestamp_granularities (word / segment) to choose how fine-grained the timestamps are.

Text-to-speech

Section titled “Text-to-speech”

/v1/audio/speech takes a JSON body with the text, a voice, and a format, and returns raw audio bytes, not JSON. Save or stream the response body directly.

Generating speech

Section titled “Generating speech”
Terminal window
curl https://api.mirapi.ai/v1/audio/speech \
  -H "Authorization: Bearer $MIRAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepseek-chat",
  "input": "Hello from MirAPI",
  "voice": "alloy",
  "response_format": "mp3"
  }' \
  -o speech.mp3
import os
from openai import OpenAI


client = OpenAI(base_url="https://api.mirapi.ai/v1", api_key=os.environ["MIRAPI_API_KEY"])


response = client.audio.speech.create(
    model="deepseek-chat",
    input="Hello from MirAPI",
    voice="alloy",
    response_format="mp3",
)


response.stream_to_file("speech.mp3")

Parameters

Section titled “Parameters”
Field Type Required Notes
model string Yes Text-to-speech model name from the catalog
input string Yes Text to synthesize (up to 4096 characters)
voice string Yes alloy, echo, fable, onyx, nova, or shimmer
response_format string No mp3 (default), opus, aac, flac, wav, pcm
speed number No 0.25–4.0 (default 1.0); supported where the model allows it

Output formats

Section titled “Output formats”

Choose the output format with response_format. mp3, opus, and aac are compressed; flac is lossless; wav and pcm are uncompressed. Use a compressed format for storage and an uncompressed one when fidelity matters more than size. The response body is the audio itself, so pipe it straight to a file.

Choosing a model

Section titled “Choosing a model”

Audio endpoints only work with models that support the task. For /v1/audio/speech pick a model with audio output; for transcription and translation pick a speech-to-text model. Browse the catalog at https://platform.mirapi.ai or query GET /v1/models, check each model’s capabilities, and send the exact id it returns. A vendor/ prefix you may see in the Platform is only for browsing and is not part of the model ID you send.

Errors, billing, and logs

Section titled “Errors, billing, and logs”
  • Errors follow the standard status codes: 401 for a missing or invalid key, 403 for a valid key that is rejected (for example, an exhausted balance or a model not on the key’s whitelist), 413 for a file that is too large, 429 for rate limiting, and 500 for an upstream failure. For 429, retry with exponential backoff; the gateway does not send a Retry-After header. Every error message ends with a request ID; include it in support tickets.
  • Billing uses a per-model price in USD, shown on each catalog entry. Audio requests appear in the Platform billing log and in GET /api/log/token, and the account-level summary is in GET /api/usage/token. When your balance runs out, requests fail with 403. Top up and the same key works again.
Section titled “Related links”