Grok STT 1.0 is SpaceXAI’s speech-to-text model. It takes audio and returns a transcription, with word-level timestamps and optional speaker diarization. The published profile also supports multichannel audio. Its useful output is the spoken content connected to the timing and, where requested, the speakers in a recording.
Identify the recording to transcribe and the way the result will be used. A meeting transcript needs the sequence of turns; an interview may need speaker labels; an editing task needs words connected to their positions in the audio. Preserve the source recording and its identifier so a reviewer can return to the original passage when a word or speaker assignment is uncertain.
Use the actual recording rather than a rewritten account of what it contains. For a multichannel source, retain its channel structure when preparing the audio. That structure and speaker diarization describe different parts of the task: channels belong to the recording, while diarization identifies speaker turns in the transcript.
Word-level timestamps connect transcribed words to the recording. They help locate a quote, review a difficult phrase or prepare a later subtitle or editing step. Keep the timestamps with the words when exporting or transforming the transcript, and check important passages against the audio.
Optional diarization adds speaker structure. Review transitions, interruptions and similar-sounding voices before relying on the assigned labels in a final document. Use stable speaker labels in downstream notes, keeping any later identification of a person distinct from the model’s speaker grouping.
A transcript can feed a summary, searchable record or caption-preparation workflow. Those later artifacts should retain the relevant transcript span and source timing. For a quote, inspect the exact audio passage; for a meeting note, distinguish what was spoken from conclusions drawn from it. The model produces the transcription, while formatting, summarization and publication follow from that actual result.
", "aboutText": "Grok STT 1.0 is SpaceXAI’s speech-to-text model. It takes audio and returns a transcription, with word-level timestamps and optional speaker diarization. The published profile also supports multichannel audio. Its useful output is the spoken content connected to the timing and, where requested, the speakers in a recording.\n\n### Prepare the recording and the transcript task\n\nIdentify the recording to transcribe and the way the result will be used. A meeting transcript needs the sequence of turns; an interview may need speaker labels; an editing task needs words connected to their positions in the audio. Preserve the source recording and its identifier so a reviewer can return to the original passage when a word or speaker assignment is uncertain.\n\nUse the actual recording rather than a rewritten account of what it contains. For a multichannel source, retain its channel structure when preparing the audio. That structure and speaker diarization describe different parts of the task: channels belong to the recording, while diarization identifies speaker turns in the transcript.\n\n### Timing and speaker structure\n\nWord-level timestamps connect transcribed words to the recording. They help locate a quote, review a difficult phrase or prepare a later subtitle or editing step. Keep the timestamps with the words when exporting or transforming the transcript, and check important passages against the audio.\n\nOptional diarization adds speaker structure. Review transitions, interruptions and similar-sounding voices before relying on the assigned labels in a final document. Use stable speaker labels in downstream notes, keeping any later identification of a person distinct from the model’s speaker grouping.\n\n### Use the transcription as source material\n\nA transcript can feed a summary, searchable record or caption-preparation workflow. Those later artifacts should retain the relevant transcript span and source timing. For a quote, inspect the exact audio passage; for a meeting note, distinguish what was spoken from conclusions drawn from it. The model produces the transcription, while formatting, summarization and publication follow from that actual result.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "412ff8137141e339c087dfa29aab27a0607fce9376ac71b240b9ecefd9bb0c4f", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "x-ai/grok-stt-1.0Grok STT 1.0 turns audio into a transcript with word-level timestamps. SpaceXAI documents optional speaker diarization and multichannel audio, making the model useful for recordings that need both spoken text and its timing or speaker structure.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Grok STT 1.0 is SpaceXAI’s speech-to-text model. It takes audio and returns a transcription, with word-level timestamps and optional speaker diarization. The published profile also supports multichannel audio. Its useful output is the spoken content connected to the timing and, where requested, the speakers in a recording.
Identify the recording to transcribe and the way the result will be used. A meeting transcript needs the sequence of turns; an interview may need speaker labels; an editing task needs words connected to their positions in the audio. Preserve the source recording and its identifier so a reviewer can return to the original passage when a word or speaker assignment is uncertain.
Use the actual recording rather than a rewritten account of what it contains. For a multichannel source, retain its channel structure when preparing the audio. That structure and speaker diarization describe different parts of the task: channels belong to the recording, while diarization identifies speaker turns in the transcript.
Word-level timestamps connect transcribed words to the recording. They help locate a quote, review a difficult phrase or prepare a later subtitle or editing step. Keep the timestamps with the words when exporting or transforming the transcript, and check important passages against the audio.
Optional diarization adds speaker structure. Review transitions, interruptions and similar-sounding voices before relying on the assigned labels in a final document. Use stable speaker labels in downstream notes, keeping any later identification of a person distinct from the model’s speaker grouping.
A transcript can feed a summary, searchable record or caption-preparation workflow. Those later artifacts should retain the relevant transcript span and source timing. For a quote, inspect the exact audio passage; for a meeting note, distinguish what was spoken from conclusions drawn from it. The model produces the transcription, while formatting, summarization and publication follow from that actual result.
POST /v1/audio/transcriptionsaudiotext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits x-ai/grok-stt-1.0 | Default— |
Fieldinput_audio | Typeobject | RequirementRequired | Values & limits | Default— |
Fieldlanguage | Typestring | RequirementOptional | Values & limits | Default— |
Fieldtemperature | Typenumber | RequirementOptional | Values & limits Minimum: 0 Maximum: 1 | Default— |
Fieldresponse_format | Typestring | RequirementOptional | Values & limits json, verbose_json | Defaultjson |
Fieldtimestamp_granularities | Typearray | RequirementOptional | Values & limits | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits | Default— |
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, input_audio |
Parametermaterial_types | Contractaudio |
Parametermaterial_conditions | ContractRead an actual WAV file and encode its real bytes for the declared JSON input_audio; no multipart route is advertised for this exact JSON-only declaration. |
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}
The displayed rates estimate the cost before generation. The final charge is calculated from the cost recorded for the original generation. Measured output duration and forecast quantities are not the final billable quantity.
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Forecast quantity | Billing unit | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Forecast quantity— | Billing unit— | Charge Input · Input tokens · Estimate for comparison only — / 1K tokens Output · Output tokens · Estimate for comparison only — / 1K tokens Input · Cache read · Estimate for comparison only — / 1K tokens Input · Cache write · Estimate for comparison only — / 1K tokens Input · Cache write, 1 hour · Estimate for comparison only — / 1K tokens |
| Configurationinput audio second | Rate schedule— | Forecast quantity— | Billing unitper input audio second | Charge Input · input audio second · Estimate for comparison only $0.0000555555555556 per input audio second |
| ConfigurationEstimated generation cost | Rate schedule— | Forecast quantityone generation estimate | Billing unit— | Charge Output · Estimated generation cost · Estimate for comparison only $0.0000555555555556 estimate before generation This estimate is not an additional charge or a fixed rate for the completed generation. |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_AUDIO_FILE:?Set the path to your actual WAV recording}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\nimport base64\naudio=Path(os.environ['AILOOT_AUDIO_FILE']).read_bytes()\nif not (audio[:4]==b'RIFF' and audio[8:12]==b'WAVE'): raise SystemExit('Supply an actual WAV audio file')\nif len(audio)>26214400: raise SystemExit('Use a documented supported large-file flow')\nrequest={'model': 'x-ai/grok-stt-1.0', 'input_audio': {'data': '${BASE64_ACTUAL_WAV_BYTES}', 'format': 'wav'}}\nrequest['input_audio']['data']=base64.b64encode(audio).decode('ascii')\nPath('request.json').write_text(json.dumps(request,ensure_ascii=False),encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/audio/transcriptions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o response.bin\n# Keep the complete original response and headers. Read every returned segment, word and usage field.\n# Preserve actual operation/task/asset IDs; continue reads of the original result without resubmitting.\nGET /v1/media/tasks/{task_id}GET /v1/media/assets/{asset_id}/contentGET /v1/media/assetsGET /v1/media/assets/{asset_id}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/media/assets \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -o owned-assets.json\n# Preserve every returned asset and follow its exact signed content URL. Do not construct a signed token.\nKeep every complete returned response, file and content part.
Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again.
Keep the returned X-Client-Request-ID for reconciliation. Read only actual returned task_id/asset_id values or the owned media library; never build a task URL from the operation ID and never resubmit creation.
| Field | Type |
|---|---|
Fieldtext | Type |
Fieldusage | Type |
Fieldsegments[] | Type |
Fieldwords[] | Type |
Fieldspeaker fields | Type |
Fieldtimestamps | Type |
Ailoot Ultra x-ai/grok-stt-1.0
Use the method paths shown above.