Speech to Text

Overview

Transcribe an audio file into text with any of 45 speech-to-text models. The default, saaras:v3, covers 22 Indian languages plus English with automatic language detection — but the model field takes any file-transcription STT id, so you can pick per request.

Endpoint: POST /v1/audio/transcriptions

Picking a model

Four models are on the free tier: saaras:v3, saaras:v4, nova-3 and whisper-large-v3-turbo.

How transcription works

1. 1

   Your app

   Upload an audio file (WAV/MP3) to

2. 2

   CallMissed gateway

   Validate the key, resolve , detect language (or use ), apply

3. 3

   Your chosen model

   Run speech recognition — defaults to if is omitted

4. 4

   Your app

   Receive (plus in )

Tip: Leave model unset to get saaras:v3, and leave language unset to let it auto-detect. Set mode=translate to get English text out of any supported language in a single call.

Basic Usage

from openai import OpenAI

client = OpenAI(
    api_key="cm_your_key",
    base_url="https://api.callmissed.com/v1"
)

with open("audio.wav", "rb") as f:
    response = client.audio.transcriptions.create(
        model="saaras:v3",
        file=f
    )

print(response.text)

Parameters

Send as multipart/form-data.

Response

json (default):

{"text": "Namaste, aap kaise hain?"}

text returns the transcript as text/plain. verbose_json adds the billed audio duration in seconds. words is always an empty array — word-level timestamps are not returned. segments is empty except on gpt-4o-transcribe-diarize, where each segment carries id, speaker, start, end and text. diarized_json returns task, duration, text and those speaker segments.

{
  "task": "transcribe",
  "language": "hi-IN",
  "duration": 4.52,
  "text": "Namaste, aap kaise hain?",
  "segments": [],
  "words": []
}

language echoes the language you sent, or "unknown" when you let the model auto-detect.

Errors

Errors use the OpenAI envelope: {"error": {"message", "type", "code"}}.

/v1/audio/translations returns the same errors.

Output Modes

mode is applied by saaras:v3 and saaras:v4. whisper-large-v3-turbo also honours translate. Every other model ignores mode and returns a plain transcript.

saaras:v4 serves all five modes on one model across 24 languages, and is free-tier like saaras:v3:

curl -X POST https://api.callmissed.com/v1/audio/transcriptions \
  -H "Authorization: Bearer cm_your_key" \
  -F file=@audio.wav \
  -F model=saaras:v4 \
  -F mode=codemix

Cartesia Ink models

Two Cartesia STT models, and they are not interchangeable — one transcribes files, the other only runs on a live voice session.

ink-whisper — the cheapest 100-language option

Cartesia's fastest and most affordable STT, with better accuracy than baseline Whisper. Its dynamic chunking cuts hallucination during pauses and silence, so audio with dead air transcribes cleanly instead of inventing text to fill gaps.

curl -X POST https://api.callmissed.com/v1/audio/transcriptions \
  -H "Authorization: Bearer cm_your_key" \
  -F file=@audio.wav \
  -F model=ink-whisper \
  -F language=hi

ink-2 — voice agents only

Cartesia's top-ranked STT for voice agents: 8% WER on AppTek's 14-accent call-centre benchmark, against 10% for Deepgram Flux and 12% for ElevenLabs. It also self-detects turns, so a voice agent needs no separate turn detector on top.

Two limits decide whether you can use it at all:

1. It cannot transcribe files. ink-2 is streaming-only. POSTing it to /v1/audio/transcriptions fails rather than quietly substituting a different model. The request is not transcribed, and the error message names the alternative:

{
  "error": {
    "message": "ink-2 is a streaming-only model and is not available for file transcription. Use ink-whisper here, or ink-2 on a voice session.",
    "type": "invalid_request_error",
    "code": "invalid_request",
    "request_id": "stt-…"
  }
}

The HTTP status is 400. deepgram-flux-general-en and deepgram-flux-general-multi fail the same way and point you to deepgram-nova-3.

Select it on a voice session or the Managed Voice Agent instead.

2. It covers five languages. The model accepts en, fr, hi, ja and es. Sending it any other language (Tamil, for example) does not raise an upstream error — it silently produces poor output. Our agent logs a warning and transcribes as en. For other languages use ink-whisper (100 languages) or an Indic model such as saaras:v3 / saaras:v4.

Deepgram feature parameters

When you select a Deepgram file-transcription model (deepgram-nova-3, deepgram-nova-2, deepgram-enhanced, etc.), these extra form fields are accepted. They are ignored for non-Deepgram models. Model-restricted features are dropped automatically when the chosen model doesn't support them.

Dialects & locales

Deepgram models accept locale-specific language codes so you can pin a dialect for best accuracy. Pass the code in the language field. Each model's exact dialect list is published in the dialects array on GET /v1/models. Examples:

• English: en-US, en-GB, en-IN, en-AU, en-NZ, en-CA, en-IE
• Spanish: es, es-419 (Latin America)
• Portuguese: pt-BR, pt-PT
• Chinese: zh-CN, zh-TW, zh-HK (Cantonese)
• Multilingual code-switching: multi (Nova-3, Nova-2)