asr-1.0
MiniMax ASR 1.0 converts audio to text and supports Russian, speaker-separated turns and timestamps.
About the model
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
A recorded conversation as text
MiniMax ASR 1.0 recognizes speech in an audio file. The manufacturer describes uses for meetings, interviews, podcasts, video audio tracks, content monitoring and conversation analysis. The model is tuned for conversational speech, noise and professional vocabulary, with an emphasis on reducing fabricated passages. In this Ailoot card, input is audio and the result is text.
Language and multiple participants
Russian and Ukrainian, English, French, German, Spanish, Italian, Portuguese and Polish are supported, as well as Chinese, Cantonese, Japanese, Korean, Thai, Vietnamese, Indonesian, Malay, Filipino, Arabic and Turkish. If no language is specified, the model automatically identifies the main one; the manufacturer separately describes mixed Chinese and English speech.
In the detailed result representation, the model can identify speakers and link turns to their times. It returns the total participant count and segments with a speaker label, start, end and text. This helps identify who said a particular line and when, without mixing different participants' turns.
Result representation
The manufacturer provides ordinary JSON with text and duration, detailed verbose_json, and SRT and WebVTT subtitles. Timestamps use sentence or segment level by default. Word-level timestamps are described for English and character-level timestamps for Chinese; these belong to formats with alignment.
Incremental text output is possible, but cannot be combined with speaker diarization or subtitle formats. This mode returns newly recognized text passages as the already-supplied file is processed. It is a stream of results, not continuous transmission of microphone audio.
Recording requirements
Declared input formats are WAV, AIFF, FLAC, ALAC in an M4A container, MP3, AAC, Opus and Ogg. A file must contain no more than 500 seconds of audio and occupy no more than 50 MB. Exceeding the duration is rejected rather than silently truncated. Raw PCM without a container is not supported.
For recording preparation, the manufacturer recommends mono 16 kHz or a compressed audio format: a high sample rate and stereo are unnecessary for recognition and increase file size. Detailed output and streaming capabilities belong to ASR 1.0; the response format available to a particular request is set through Ailoot's controls.
Ailoot · Speech-to-text POST /v1/audio/transcriptions asr-1.0
asr-1.0Overview
MiniMax ASR 1.0 converts audio to text and supports Russian, speaker-separated turns and timestamps.
- Accepted inputs
- Audio
- Results
- Text
Available in Ailoot · inputs & methods
Ailoot · Speech-to-text POST /v1/audio/transcriptions
- Input types
audio- Output types
text- Output format
- json
| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits asr-1.0 | Default— |
Fieldfile | Typefile | RequirementRequired | Values & limits Maximum bytes: 52,428,800 File formats: wav, mp3, m4a, ogg, webm, flac Content type: multipart/form-data Maximum duration (exclusive), seconds: 500 | Default— |
Fieldresponse_format | Typestring | RequirementOptional | Values & limits json | Default— |
Input material combinations
speech_to_text · Required: actual audio file
Method parameters and lifecycle
| Parameter | Contract |
|---|---|
Parametermaterial_types | Contractaudio |
Parameterrequired | Contractnull |
Parameteroptional_controls | Contractnull |
Lifecycle: synchronous_result_then_owned_library
GET /v1/media/tasks/{task_id} · actual returned task_id or media library record
GET /v1/media/assets/{asset_id}/content
GET /v1/media/assets
GET /v1/media/assets/{asset_id}
Method shapes and IDs are exact; supplier capability is separate from admission.
Pricing
Ailoot method rates
POST /v1/audio/transcriptions- Input
- $0.38 per hour of audio
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
Example requests
Ailoot · Speech-to-text
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_AUDIO_FILE:?Set your actual MP3 recording}"
export AILOOT_AUDIO_FILE
python3 - <<'PY_REQUEST'
import os
from pathlib import Path
f=Path(os.environ["AILOOT_AUDIO_FILE"])
if not f.is_file() or f.suffix.lower()!=".mp3":raise SystemExit("Choose your actual MP3 recording")
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/audio/transcriptions \
-H "Authorization: Bearer $AILOOT_API_KEY" \
--form-string model=asr-1.0 -F "file=@$AILOOT_AUDIO_FILE" \
-D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
Receive and save results
Ailoot · Speech-to-text
json
GET /v1/media/tasks/{task_id}GET /v1/media/assets/{asset_id}/contentGET /v1/media/assetsGET /v1/media/assets/{asset_id}
Keep all completed results
Keep every complete returned response, file and content part.
Retain complete JSON, not only text; preserve every available segment/speaker/timestamp and actual task/asset identity.
If the original response needs checking
Retain original operation_id/X-Client-Request-ID for reconciliation without resubmission; no dedicated audio poll route.
Response fields
| Field | Type |
|---|---|
Fieldtext | Typestring |
Fieldsegments[] | Typeobject |
Fieldtask_id | Typestring |
Fieldasset_url | Typestring |
Fieldusage | Typeobject |
Errors and next steps
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Responseserver_error | ConditionThe returned response says the operation or result requires a check | Next stepKeep the original returned operation/task ID, request headers and response; continue supported reads of that original operation. Do not resubmit the creation request. |
Aliases
Model aliases
Ailoot asr-1.0
Method path aliases
Use the method paths shown above.
Related caller IDs
FAQ · asr-1.0
- What inputs and results are available?
POST /v1/audio/transcriptions·asr-1.0:audio→text- Which fields does the request use?
POST /v1/audio/transcriptions·asr-1.0:model,file,response_format