Source: https://ailoot.ai/models/en/deepgram-nova-3/ Canonical: https://ailoot.ai/models/en/deepgram-nova-3/ Language: en # Deepgram: Nova-3 [Markdown](https://ailoot.ai/models/en/deepgram-nova-3/index.md) · [JSON](https://ailoot.ai/models/en/deepgram-nova-3/facts.json) ## [Deepgram: Nova-3](https://ailoot.ai/models/en/deepgram-nova-3/) Nova-3 is Deepgram’s general-purpose speech-to-text model for recorded and streaming audio. It supports monolingual recognition, a defined multilingual code-switching mode and keyterm prompting, returning transcripts with word timing and confidence information. - [**Ailoot Ultra · Speech recognition** `POST /v1/audio/transcriptions` `deepgram/nova-3`](https://ailoot.ai/models/en/deepgram-nova-3/#method-0) About the model This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below. Nova-3 is Deepgram’s general-purpose speech-recognition model for converting audio into text. The producer recommends it for meetings, event captions, multi-speaker recordings and challenging conditions such as noise or distant microphones, using either pre-recorded or streaming transcription. Its useful result is recognized speech with timing and confidence information that remains connected to the source audio. #### Choose the language workflow The documented default language is English. A monolingual request selects the spoken language or supported locale. The current general-model table includes English regional variants, Spanish, French, German, Russian, Portuguese, Japanese, Italian, Dutch, Arabic, Chinese scripts and many other languages, including Kazakh. Select from the producer’s supported codes rather than assuming that any locale name is accepted. The multilingual setting is a separate code-switching workflow. The current Nova-3 table lists ten languages for it: English, Spanish, French, German, Hindi, Russian, Portuguese, Japanese, Italian and Dutch. This set is not identical to the larger monolingual list. For a recording that alternates between supported languages, prepare the multilingual mode instead of forcing the whole conversation into an unrelated single-language setting. Preserve what was spoken before preparing any translated or summarized version. #### Recorded audio and transcript preparation Deepgram’s file workflow accepts uploaded audio bytes or a reference to an audio file. Save the returned transcript when the request completes; the producer does not store transcripts for later retrieval. Common documented input formats and encodings include MP3, MP4, MP2, AAC, WAV, FLAC, PCM, M4A, Ogg, Opus and WebM. Preserve the actual format and channel information with the recording. Give the recording a stable identifier and keep the result associated with the correct source and its channel information. For a meeting, review participant names and technical terms while listening to the original sound. For a lecture or event, retain the sequence of the audio so a later caption or search result can locate the relevant passage. The producer’s pre-recorded guide lists a maximum file size of 2 GB and recommends extracting the audio stream from a large video file. It also documents a ten-minute processing timeout for Nova requests. That timeout concerns how long the request processes, not a ten-minute maximum recording duration. A useful result includes the ending of the intended recording; a partially retained transcript should not be treated as the complete text. #### Read the words, times and confidence The documented JSON response includes transcript alternatives and recognized words, with each word’s start and end time in seconds from the beginning of the audio and a confidence value. For a multi-speaker transcript, the producer’s optional diarization assigns a speaker label to each word. Pre-recorded diarization also returns speaker confidence; streaming diarization returns the speaker label. Review those labels against the voices in the recording. Overall transcript confidence is also reported on a 0–1 scale. When smart formatting is requested, the result can include punctuation and capitalization as punctuated words, along with readable paragraph information. Use those fields according to their meaning. A word time locates recognized speech, while confidence is the model’s indication of reliability, not proof that a difficult name or quantity was heard correctly. For caption preparation, retain the timing alongside reviewed wording and inspect the boundaries against the sound. For a readable editorial version, keep changes distinguishable from the recognized transcript rather than silently replacing uncertain words with a plausible story. #### Streaming recognition and final segments Nova’s streaming workflow returns text as audio arrives, with interim and final results. The is\_final indicator distinguishes text that may be revised from a finalized segment. The speech\_final indicator relates to endpointing of a spoken segment. Keep these signals distinct from merely receiving a non-empty transcript, and retain the final segments in their audio order when preparing the completed record. Nova-3 is general ASR rather than the separate Flux conversational model with model-native turn detection. Nova marks transcript finality and speech endpoints; Flux supplies its own conversational turn-state events. Choose the transcription workflow around whether the audio is already recorded or is arriving live, while using the actual final output as the artifact to retain. #### Keyterms for vocabulary that matters Nova-3’s documented Keyterm Prompting supports monolingual and multilingual transcription and adapts recognition toward important terms without retraining the model. Supply relevant names, product terms, acronyms or multi-word phrases that may actually be spoken. The guide limits the combined keyterm input to 500 tokens and recommends focusing on the most important vocabulary rather than adding common words indiscriminately. The producer’s syntax uses plain terms, with a separate keyterm entry for each term. A multi-word phrase stays one phrase. Legacy keyword weights or intensifiers, and joining separate terms with commas, semicolons or line breaks, are not equivalent: the interface can accept them as one literal value while providing no intended boost. Use the correct capitalization for names, then check the transcript because audio context and smart formatting can still change the final written form. #### Model-family boundaries and useful results The general Nova-3 profile is distinct from the separately named Medical and Pharma options. Vocabulary prompting does not turn it into another edition, and specialized models’ language coverage or behavior should not be assumed for the general model. Additional transcript-processing features are choices in the producer’s speech workflow, not evidence that recognition has produced a summary, translation or other artifact that was never requested. A useful Nova-3 deliverable can be a searchable meeting transcript, caption-ready wording with word timings, or a record of a multilingual conversation. Retain the audio identifier, selected language workflow, final text and any useful confidence or timing fields. Check unclear names, numbers, overlapping voices and language changes against the original recording, and keep the actual recognized speech available for the next content-processing step. **Ailoot Ultra · Speech recognition** `POST /v1/audio/transcriptions` `deepgram/nova-3` [`deepgram/nova-3`](https://ailoot.ai/models/en/#m=deepgram%2Fnova-3&route=Ultra&caller=deepgram%2Fnova-3&fmt=transcriptions) Deepgram /`deepgram/nova-3` ### Overview Nova-3 is Deepgram’s general-purpose speech-to-text model for recorded and streaming audio. It supports monolingual recognition, a defined multilingual code-switching mode and keyterm prompting, returning transcripts with word timing and confidence information. Accepted inputs Audio Results transcription ### Available in Ailoot · inputs & methods **Ailoot Ultra · Speech recognition** `POST /v1/audio/transcriptions` Input types `audio` Output types `transcription` Output format json | Field | Type | Requirement | Values & limits | Default | | --- | --- | --- | --- | --- | | Field`model` | Type`string` | RequirementRequired | Values & limits deepgram/nova-3 | Default— | | Field`input_audio` | Type`object` | RequirementRequired | Values & limits | Default— | | Field`language` | Type`string` | RequirementOptional | Values & limits | Default— | | Field`temperature` | Type`number` | RequirementOptional | Values & limits Minimum: 0 Maximum: 1 | Default— | | Field`response_format` | Type`string` | RequirementOptional | Values & limits json, verbose\_json | Defaultjson | | Field`timestamp_granularities` | Type`array` | RequirementOptional | Values & limits | Default— | | Field`provider` | Type`object` | RequirementOptional | Values & limits | Default— | Input material combinations **speech\_to\_text** · Required: actual matching-format audio file Method parameters and lifecycle | Parameter | Contract | | --- | --- | | Parameter`content_types` | Contractapplication/json, multipart/form-data | | Parameter`required` | Contractmodel, input\_audio | | Parameter`material_types` | Contractaudio | | Parameter`JSON_audio` | Contractactual raw audio bytes in base64 plus matching format | | Parameter`multipart_required` | Contractmodel, file | | Parameter`multipart_cap_bytes` | Contract26214400 | | Parameter`optional_controls` | Contractlanguage, temperature, response\_format, timestamp\_granularities, provider | | Parameter`default_response_format` | Contractjson | | Parameter`optional_features` | ContractVerbose output, diarize/keyterms and URL/larger inline audio require the exact model/provider capability and tariff. | 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}` Use the exact model and documented input fields. Keep the complete response, every actual output and original returned IDs. ### Pricing Tariff references do not add request options. Supported parameters are listed for the selected method. Fast mode Not specified When fast mode is selected Flex mode Not specified When flex mode is selected Maximum reasoning effort Not specified When maximum reasoning effort uses the default adjustment #### Ailoot rates #### Prices by configuration Match each charge to the conditions shown. Use one rate for each set of alternative configurations. | Configuration | Rate schedule | Billing unit | Charge | | --- | --- | --- | --- | | ConfigurationBase token rates | Rate scheduleBase rate | Billing unit— | Charge Input · Input tokens **—** / 1K tokens Output · Output tokens **—** / 1K tokens Input · Cache read **—** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens | | ConfigurationUltra | Rate schedule— | Billing unitper audio input second | Charge Input · audio input second **$0.0001433333333334** per audio input second | 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 →](https://ailoot.ai/docs/en/billing/reserve/) #### Reference tariff details Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates. Deepgram: Nova-3 #### Prices by configuration | Configuration | Billing conditions | Charge | | --- | --- | --- | | ConfigurationDeepgram: Nova-3 · Default configuration | Billing conditionsDefault configuration | Charge Input · Input audio seconds **≈$0.000143** per input audio second | ### Example requests #### Ailoot Ultra · Speech recognition curl · exact native body and complete result ```bash set -eu : "${AILOOT_API_KEY:?Set your Ailoot API key}" : "${AILOOT_AUDIO_FILE:?Set the path to your actual WAV recording}" python3 - <<'PY_REQUEST' import json,os from pathlib import Path import base64 audio=Path(os.environ['AILOOT_AUDIO_FILE']).read_bytes() if not (audio[:4]==b'RIFF' and audio[8:12]==b'WAVE'): raise SystemExit('Supply an actual WAV audio file') if len(audio)>26214400: raise SystemExit('Use a documented supported large-file flow') request={'model': 'deepgram/nova-3', 'input_audio': {'data': '${BASE64_ACTUAL_WAV_BYTES}', 'format': 'wav'}} request['input_audio']['data']=base64.b64encode(audio).decode('ascii') Path('request.json').write_text(json.dumps(request,ensure_ascii=False),encoding='utf-8') PY_REQUEST curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \ --data-binary @request.json -D response-headers.txt -o response.bin # Keep the complete original response and headers. Read every returned segment, word and usage field. # Preserve actual operation/task/asset IDs; continue reads of the original result without resubmitting. ``` ### Receive and save results #### Ailoot Ultra · Speech recognition json - `GET /v1/media/tasks/{task_id}` - `GET /v1/media/assets/{asset_id}/content` - `GET /v1/media/assets` - `GET /v1/media/assets/{asset_id}` ##### Keep all completed results Keep every complete returned response, file and content part. Complete original JSON, all available text/segments/words/speakers/timestamps and usage. ##### If the original response needs checking Retain original operation\_id/X-Client-Request-ID and original response. Read actual owned task/asset records without resubmitting; no dedicated audio poll URL is constructed. Response fields | Field | Type | | --- | --- | | Field`text` | Typestring | | Field`usage` | Typeobject | | Field`segments[]` | Typeobject | | Field`words[]` | Typeobject | ### Aliases #### Model aliases **Ailoot Ultra** [`deepgram/nova-3`](https://ailoot.ai/models/en/#m=deepgram%2Fnova-3&route=Ultra&caller=deepgram%2Fnova-3&fmt=transcriptions) #### Method path aliases Use the method paths shown above. #### Related caller IDs [`deepgram/nova-3`](https://ailoot.ai/models/en/#m=deepgram%2Fnova-3&route=Ultra&caller=deepgram%2Fnova-3&fmt=transcriptions) FAQ · Deepgram: Nova-3 What inputs and results are available? `POST /v1/audio/transcriptions` · `deepgram/nova-3`: `audio` → `transcription` Which fields does the request use? `POST /v1/audio/transcriptions` · `deepgram/nova-3`: `model`, `input_audio`, `language`, `temperature`, `response_format`, `timestamp_granularities`, `provider` What limits apply? `POST /v1/audio/transcriptions` · `deepgram/nova-3`: `temperature.minimum`: `0`; `temperature.maximum`: `1` Connect Ailoot to Claude Code, OpenCode, Hermes or your own app. ## The company and its project portfolio The company and its project portfolio: millions of customers; monthly sales in the billions. ## Buy tokens at a discount. Subscription discounts for regular use. Promo codes offer up to 50% off token purchases. Subscription Choose a discounted plan for your regular requests. Promo code: up to 50% off Enter your code at checkout. The price updates to reflect the current promotion. Spending in your history The model, tokens and amount are recorded for each request. [Choose a subscription](https://ailoot.ai/docs/en/billing/subscriptions/) · [View model prices](https://ailoot.ai/models/en/) ## Connect the API to a product you sell. Use Ailoot in SaaS, apps and bots under its official service offer and licence agreement. Request a reseller licence for resale. Commercial application Add text, image, video and audio generation to paid features in your service. Reseller licence Send a description of your project and how you provide access. Request written terms for use and resale. Documents on the website The service offer, licence agreement and data processing policy are available before you connect. [Request a reseller licence](mailto:support@ailoot.ai) · [Service offer and licence agreement](https://ailoot.ai/legal/offer?lang=en) ## Ailoot · The company and its project portfolio Ailoot combines established operating experience, a large client base, stable service and ongoing KPI control. The company and its project portfolio: millions of customers; monthly sales in the billions. Ailoot brings that operating experience to API access for AI features in customer products, agents, applications and automations.