Speech to Text
Transcribe audio to text across 47 STT models — Indic-first saaras, Cartesia Ink, and Deepgram Nova.
Overview
Transcribe an audio file into text with any of 47 speech-to-text models. The default, saaras:v4, 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
| If you need | Use | Why |
|---|---|---|
| Indian languages, or code-mixed Hinglish | saaras:v4 | Purpose-built for Indic phonetics; 23 languages, all five output modes |
| The widest language coverage | ink-whisper | 100 languages, and cheaper per hour than the Indic models |
| English call-centre audio | deepgram-nova-3 | Strong on accented and noisy telephony English |
| Clinical or pharmaceutical audio | deepgram-nova-3-medical, deepgram-nova-3-pharma or scribe_v2_medical | Tuned for medical terms and drug names; deepgram-nova-3-pharma is English only; scribe_v2_medical hears 100 languages |
| Highest accuracy on recorded audio, any of 100 languages | scribe_v2 | ElevenLabs Scribe v2: automatic language detection, 13 Indian languages — see ElevenLabs Scribe models |
| Long recordings, up to 2 hours per file (preview) | mai-transcribe-2 | 60 languages with automatic detection — see MAI-Transcribe-2 |
| Turn detection built into the model | ink-2, assemblyai-universal-3.6-pro or deepgram-flux-general-en | Voice sessions only — see the note below |
One model is on the free tier: saaras:v4. The retired nova-3 and
whisper-large-v3-turbo IDs still work and stay free; they are answered by
deepgram-nova-3 and whisper — see
Retired and deprecated models.
The retired nova-3 ID and deepgram-nova-3 are the same model at different
prices: nova-3 stays on the free plan at its old rate. Full per-model pricing:
Models.
How transcription works
- 1
Your app
Upload an audio file (WAV/MP3) to
- 2
CallMissed gateway
Validate the key, resolve , detect language (or use ), apply
- 3
Your chosen model
Run speech recognition — defaults to if is omitted
- 4
Your app
Receive (plus in )
Tip
Leave model unset to get saaras:v4, 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.
Streaming-only models cannot transcribe files. ink-2, the Deepgram Flux
models, assemblyai-universal-3.6-pro and inworld-stt-1 do turn detection as part of the model, which only makes sense on a live
stream. Sending one here returns an error naming the file-transcription
alternative rather than silently substituting a different model — see
Cartesia Ink models.
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:v4",
file=f
)
print(response.text)import OpenAI from "openai";
import fs from "fs";
const client = new OpenAI({
apiKey: "cm_your_key",
baseURL: "https://api.callmissed.com/v1",
});
const response = await client.audio.transcriptions.create({
model: "saaras:v4",
file: fs.createReadStream("audio.wav"),
});
console.log(response.text);curl -X POST https://api.callmissed.com/v1/audio/transcriptions \
-H "Authorization: Bearer cm_your_key" \
-F [email protected] \
-F model=saaras:v4Parameters
Send as multipart/form-data.
| Parameter | Type | Required | Description |
|---|---|---|---|
file | file | Yes | Audio file (WAV, MP3, etc.), up to 25 MB. An empty file returns 400. Some models accept less per request: saaras:v4 takes at most 30 seconds of audio, gnani-prisma-v3.0 (and its retired ID gnani-prisma-v2.5) at most 30 seconds, and whisper, gpt-4o-transcribe, gpt-4o-mini-transcribe and gpt-4o-transcribe-diarize at most 25,000,000 bytes |
model | string | No | Default saaras:v4. Any file-transcription STT model ID from Models. ink-2, scribe_v2_realtime and the Flux models are not valid here — see Cartesia Ink models and ElevenLabs Scribe models |
language | string | No | Language code; auto-detected if omitted. For saaras:v4 use a locale such as hi-IN or ta-IN — a code the model does not support falls back to auto-detection. For gnani-prisma-v3.0 use one of hi-IN, bn-IN, ta-IN, te-IN, kn-IN, ml-IN, mr-IN, gu-IN, pa-IN, en-IN, a comma-separated list of up to 4 of them, or indic-auto to detect the language; a base code such as hi is read as hi-IN |
mode | string | No | Output mode — see below. Default transcribe; any other value returns 422 |
response_format | string | No | json (default), text, verbose_json, or diarized_json. Any other value is answered as json |
temperature | number | No | 0–2. Accepted for OpenAI SDK compatibility; currently not forwarded to the model |
prompt | string | No | Accepted for OpenAI SDK compatibility; currently not forwarded to the model |
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"}}.
| Status | code | When |
|---|---|---|
400 | invalid_request | file is empty; the audio or a parameter was rejected (format, size, language); or the model is streaming-only or not available for file transcription. The message says which |
400 | audio_too_long | The audio is longer than the model accepts per request (see file above). Use a model without a duration limit, such as deepgram-nova-3 |
402 | insufficient_credits | Credit balance is exhausted |
403 | permission_denied | The API key does not have the stt permission, or the model is not available on your plan |
404 | model_not_found | model is not a known STT model ID |
422 | — | A form field fails validation (for example an unknown mode, or temperature outside 0–2) |
413 | file_too_large | The file is larger than 25 MB, or than the model accepts (see file above) |
429 | quota_exceeded | Plan usage limit reached |
429 | rate_limit_exceeded | Transcription is rate limited right now. Retry with backoff |
503 | service_unavailable | Transcription is temporarily unavailable. Retry shortly. /v1/audio/speech uses the same code |
503 | provider_error, upstream_timeout, upstream_unavailable | The model failed to transcribe the file. The response includes a request_id |
/v1/audio/translations returns the same errors.
Output Modes
| Mode | Description |
|---|---|
transcribe | Standard transcription (default) |
translate | Transcribe and translate to English |
verbatim | Exact transcription including filler words |
translit | Transliteration to Latin script |
codemix | Code-mixed output (Indic + English) |
mode is applied by saaras:v4. whisper also
honours translate. Every other model ignores mode and returns a plain
transcript.
saaras:v4 serves all five modes on one model across 23 languages, and is on the free tier:
curl -X POST https://api.callmissed.com/v1/audio/transcriptions \
-H "Authorization: Bearer cm_your_key" \
-F [email protected] \
-F model=saaras:v4 \
-F mode=codemixCartesia Ink models
Two Cartesia STT models, and they are not interchangeable — one transcribes files, the other only runs on a live voice session.
| Model | Price | Languages | File transcription | Voice sessions |
|---|---|---|---|---|
ink-whisper | $0.1875 / hr | 100 (incl. Hindi, Urdu, Tamil) | Yes | Yes |
ink-2 | $0.5625 / hr | 5: en, fr, hi, ja, es | No | Yes |
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 [email protected] \
-F model=ink-whisper \
-F language=hiink-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:v4.
ElevenLabs Scribe models
Three ElevenLabs speech-to-text models. Two transcribe files; the third only runs on a live voice session. All three hear the same 100 languages, including Hindi, Bengali, Tamil, Telugu, Marathi, Gujarati, Kannada, Malayalam, Punjabi, Odia, Assamese, Urdu and Sinhala, and detect the language automatically when language is left out. Paid plans only.
| Model | Price | File transcription | Voice sessions |
|---|---|---|---|
scribe_v2 | $0.2292 / hr | Yes | No |
scribe_v2_medical | $0.2292 / hr | Yes | No |
scribe_v2_realtime | $0.4063 / hr | No | Yes |
scribe_v2 is ElevenLabs' state-of-the-art recognizer for recorded audio. scribe_v2_medical is the same API and price, fine-tuned for clinical audio (clinician-patient conversations, dictation, intake calls) with 35% fewer errors on it and the same accuracy on everyday speech. language takes a base code (hi; hi-IN is reduced to hi); a code the model does not hear is ignored and the language is detected instead. mode other than transcribe is not applied. Silence counts toward the billed duration.
scribe_v2_realtime is the streaming model for voice agents (~150 ms to a committed transcript upstream): select it with stt_model on an agent or a voice session. It has no turn detection of its own, so the agent's turn detection applies. POSTing it here returns 400; use scribe_v2 for files.
curl -X POST https://api.callmissed.com/v1/audio/transcriptions \
-H "Authorization: Bearer cm_your_key" \
-F "model=scribe_v2" \
-F "language=hi" \
-F "[email protected]"Voice-session-only models
Four more speech-to-text models run only on a live voice session, selected with stt_model on an agent or a voice session. POSTing any of them to /v1/audio/transcriptions returns 400. For files, use saaras:v4, ink-whisper or deepgram-nova-3.
| Model | Price | Languages | Turn detection |
|---|---|---|---|
assemblyai-universal-3.6-pro | $0.4688 / hr | 50 | Built into the model |
inworld-stt-1 | $0.1563 / hr | English only (en, en-US) | Not built in |
microsoft-speech-stt | $1.0417 / hr | 81 (148 locales), one per call | Not built in |
scribe_v2_realtime | $0.4063 / hr | 100, auto-detected | Not built in |
assemblyai-universal-3.6-pro is AssemblyAI's newest streaming model. It ends the caller's turn itself, so the agent needs no separate turn detector on top, and it auto-detects and code-switches, so the language you set is a hint. Languages include English (with en-IN, en-US, en-GB, en-AU, en-CA, en-NZ), Spanish, French, German, Italian, Portuguese, Turkish, Dutch, Swedish, Norwegian, Danish, Finnish, Hindi, Marathi, Urdu, Vietnamese, Arabic, Hebrew, Japanese, Chinese, Cantonese, Russian, Korean, Catalan, Galician, Romanian, Estonian, Persian, Afrikaans, Zulu and Xhosa.
inworld-stt-1 is Inworld's low-cost streaming model and hears English only. For any other language use assemblyai-universal-3.6-pro, saaras:v4 or deepgram-nova-3.
scribe_v2_realtime is ElevenLabs' real-time Scribe model: 100 languages with automatic detection, so a multilingual agent can follow the caller. See ElevenLabs Scribe models.
microsoft-speech-stt is Microsoft's real-time streaming recognizer, processed in India. It hears 81 languages (148 locales), including Hindi, Bengali, Tamil, Telugu, Marathi, Gujarati, Kannada, Malayalam, Punjabi, Odia, Assamese, Urdu, Bhojpuri and Indian English. It recognises one language per call: it does not auto-detect or follow a caller who switches language, so set the agent's language to the one the caller speaks. It has no turn detection of its own, so the agent's turn detection applies. Keyterms you set on the agent (stt_keyterms) are applied as a phrase list.
mai-transcribe-2 (preview)
mai-transcribe-2 is Microsoft AI's MAI-Transcribe-2, $0.375 / hour. It is preview. It transcribes files on POST /v1/audio/transcriptions only: it is not available in voice sessions, and POST /v1/audio/translations refuses it.
- Languages. 60:
af,ar,as,az,bg,bn,bs,ca,cs,da,de,el,en,es,et,fa,fi,fil,fr,gl,gu,he,hi,hu,hy,id,is,it,ja,kk,kn,ko,lt,lv,mk,ml,mr,ms,nb,ne,nl,or,pa,pl,pt,ro,ru,sk,sl,sv,sw,ta,te,th,tr,uk,ur,vi,yue,zh. - Language detection. Leave
languageout and the language is detected automatically, including Hinglish and other code-switching.languagetakes one code;hiandhi-INboth work. A language not in the list returns400. - Files. Up to 2 hours of audio per file and the route's 25 MB upload limit. WAV, MP3, FLAC and Ogg are accepted.
response_formatisjson,textorverbose_json. - Plan and hosting. Paid plans only, never a default, and not processed in India.
- Preview. Microsoft ships this model as a public preview with no SLA, and may change or retire it at short notice. If it is retired, the ID keeps working and is answered by a named successor, as described in Retired and deprecated models, so the transcript may differ. Use a generally available model for production-critical workloads.
curl -X POST https://api.callmissed.com/v1/audio/transcriptions \
-H "Authorization: Bearer cm_your_key" \
-F "model=mai-transcribe-2" \
-F "[email protected]"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.
| Parameter | Type | Description |
|---|---|---|
diarize | boolean | Label each speaker ([Speaker 0], [Speaker 1], …) |
utterances | boolean | Segment the transcript into utterances |
utt_split | number | Silence gap (seconds, 0–10) used to split utterances |
paragraphs | boolean | Split the transcript into paragraphs |
numerals | boolean | Write numbers as digits (e.g. "five" → "5") |
measurements | boolean | Abbreviate measurement units (English) |
dictation | boolean | Convert spoken "comma"/"period" to punctuation (English) |
profanity_filter | boolean | Mask recognized profanity with **** |
filler_words | boolean | Keep "uh"/"um" (Nova / Nova-2 / Nova-3) |
multichannel | boolean | Transcribe each audio channel independently |
detect_entities | boolean | Tag entities like names and locations (English) |
detect_language | string | true to auto-detect, or repeat with codes to restrict |
redact | string | pci, pii, phi, numbers, or a specific entity type (repeatable) |
keyterm | string | Boost recognition of a term/phrase (Nova-3, including medical and pharma; repeatable) |
language_hint | string | Steer language=multi toward the languages you expect, e.g. language_hint=hi and language_hint=en. deepgram-nova-3 only, and only with language=multi; ignored otherwise, as are codes Deepgram does not list. Repeatable |
keywords | string | keyword:intensifier boost/suppress (Nova-2 / legacy; repeatable) |
search | string | Phonetically search the audio for a term (repeatable) |
replace | string | find:replacement substitution (repeatable) |
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-3 Medical, Nova-2). Nova-3 Medical covers 10 languages inmulti;deepgram-nova-3-pharmais English only