oneringaiv2
Documentation/Speech-to-Text (STT)
v2.0.0-beta.1Snapshot bebdcd1Markdown ↗

Speech-to-Text (STT)

Speech-to-Text (STT)

Transcribe audio to text

SpeechToText class

📍 src/core/SpeechToText.ts:54

SpeechToText capability class Provides speech-to-text transcription with model introspection

Example:

typescript
const stt = SpeechToText.create({
  connector: 'openai',
  model: 'whisper-1',
});

const result = await stt.transcribe(audioBuffer);
console.log(result.text);

const detailed = await stt.transcribeWithTimestamps(audioBuffer, 'word');
console.log(detailed.words);
Static Methods

static create()

Create a new SpeechToText instance

typescript
static create(config: SpeechToTextConfig): SpeechToText

Parameters:

  • config: SpeechToTextConfig

Returns: SpeechToText

Methods

transcribe()

Transcribe audio to text

typescript
async transcribe(
    audio: Buffer | string,
    options?: Partial<Omit<STTOptions, 'model' | 'audio'>>
  ): Promise<STTResponse>

Parameters:

  • audio: string | Buffer<ArrayBufferLike>
  • options: Partial<Omit<STTOptions, "model" | "audio">> | undefined (optional)

Returns: Promise<STTResponse>

supportsStreaming()

Whether the current provider exposes live streaming transcription.

typescript
supportsStreaming(): boolean

Returns: boolean

transcribeStream()

Stream raw audio to a live STT session and receive interim/final transcript events. The caller is responsible for yielding audio in real-time-paced chunks.

typescript
transcribeStream(
    audio: AsyncIterable<STTStreamInput> | Iterable<STTStreamInput>,
    options: Partial<Omit<STTStreamOptions, 'model' | 'audio'>> = {}
  ): AsyncIterableIterator<STTStreamEvent>

Parameters:

  • audio: AsyncIterable<STTStreamInput> | Iterable<STTStreamInput>
  • options: Partial<Omit<STTStreamOptions, "model" | "audio">> (optional) (default: {})

Returns: AsyncIterableIterator<STTStreamEvent>

transcribeFile()

Transcribe audio file by path

typescript
async transcribeFile(
    filePath: string,
    options?: Partial<Omit<STTOptions, 'model' | 'audio'>>
  ): Promise<STTResponse>

Parameters:

  • filePath: string
  • options: Partial<Omit<STTOptions, "model" | "audio">> | undefined (optional)

Returns: Promise<STTResponse>

transcribeWithTimestamps()

Transcribe audio with word or segment timestamps

typescript
async transcribeWithTimestamps(
    audio: Buffer | string,
    granularity: 'word' | 'segment' = 'segment',
    options?: Partial<Omit<STTOptions, 'model' | 'audio' | 'includeTimestamps' | 'timestampGranularity'>>
  ): Promise<STTResponse>

Parameters:

  • audio: string | Buffer<ArrayBufferLike>
  • granularity: "word" | "segment" (optional) (default: 'segment')
  • options: Partial<Omit<STTOptions, "model" | "audio" | "includeTimestamps" | "timestampGranularity">> | undefined (optional)

Returns: Promise<STTResponse>

translate()

Translate audio to English text Note: Only supported by some models (e.g., Whisper)

typescript
async translate(
    audio: Buffer | string,
    options?: Partial<Omit<STTOptions, 'model' | 'audio'>>
  ): Promise<STTResponse>

Parameters:

  • audio: string | Buffer<ArrayBufferLike>
  • options: Partial<Omit<STTOptions, "model" | "audio">> | undefined (optional)

Returns: Promise<STTResponse>

getModelInfo()

Get model information for current or specified model

typescript
getModelInfo(model?: string): ISTTModelDescription

Parameters:

  • model: string | undefined (optional)

Returns: ISTTModelDescription

getModelCapabilities()

Get model capabilities

typescript
getModelCapabilities(model?: string)

Parameters:

  • model: string | undefined (optional)

Returns: STTModelCapabilities

listAvailableModels()

List all available models for this provider's vendor

typescript
listAvailableModels(): ISTTModelDescription[]

Returns: ISTTModelDescription[]

supportsFeature()

Check if a specific feature is supported by the model

typescript
supportsFeature(
    feature: keyof ISTTModelDescription['capabilities']['features'],
    model?: string
  ): boolean

Parameters:

  • feature: "translation" | "diarization" | "streaming" | "punctuation" | "profanityFilter"
  • model: string | undefined (optional)

Returns: boolean

getSupportedInputFormats()

Get supported input audio formats

typescript
getSupportedInputFormats(model?: string): readonly string[] | string[]

Parameters:

  • model: string | undefined (optional)

Returns: readonly string[] | string[]

getSupportedOutputFormats()

Get supported output formats

typescript
getSupportedOutputFormats(model?: string): readonly string[]

Parameters:

  • model: string | undefined (optional)

Returns: readonly string[]

getSupportedLanguages()

Get supported languages (empty array = auto-detect all)

typescript
getSupportedLanguages(model?: string): readonly string[]

Parameters:

  • model: string | undefined (optional)

Returns: readonly string[]

supportsTimestamps()

Check if timestamps are supported

typescript
supportsTimestamps(model?: string): boolean

Parameters:

  • model: string | undefined (optional)

Returns: boolean

supportsTranslation()

Check if translation is supported

typescript
supportsTranslation(model?: string): boolean

Parameters:

  • model: string | undefined (optional)

Returns: boolean

supportsDiarization()

Check if speaker diarization is supported

typescript
supportsDiarization(model?: string): boolean

Parameters:

  • model: string | undefined (optional)

Returns: boolean

getTimestampGranularities()

Get timestamp granularities supported

typescript
getTimestampGranularities(model?: string): ('word' | 'segment')[] | undefined

Parameters:

  • model: string | undefined (optional)

Returns: ("word" | "segment")[] | undefined

setModel()

Update default model

typescript
setModel(model: string): void

Parameters:

  • model: string

Returns: void

setLanguage()

Update default language

typescript
setLanguage(language: string): void

Parameters:

  • language: string

Returns: void

setTemperature()

Update default temperature

typescript
setTemperature(temperature: number): void

Parameters:

  • temperature: number

Returns: void

ISTTModelDescription interface

📍 src/domain/entities/STTModel.ts:80

Complete STT model description

Properties
Property Type Description
capabilities capabilities: STTModelCapabilities; -
pricing? pricing?: STTModelPricing; -

SpeechToTextConfig interface

📍 src/core/SpeechToText.ts:22

Configuration for SpeechToText capability

Properties
Property Type Description
connector `connector: string Connector;`
model? model?: string; Default model to use
language? language?: string; Default language (ISO-639-1 code)
temperature? temperature?: number; Default temperature for sampling

STTModelCapabilities interface

📍 src/domain/entities/STTModel.ts:22

STT model capabilities

Properties
Property Type Description
inputFormats `inputFormats: readonly string[] string[];`
outputFormats outputFormats: STTOutputFormat[]; Supported output formats
languages languages: string[]; Supported languages (empty = auto-detect all)
timestamps `timestamps: { 
supported: boolean;
granularities?: ('word' | 'segment')[];

};| Timestamp support | |features|features: { /** Translation to English / translation: boolean; /* Speaker identification / diarization: boolean; /* Real-time streaming / streaming: boolean; /* Automatic punctuation / punctuation: boolean; /* Profanity filtering / profanityFilter: boolean; };| Feature support flags | |limits|limits: { /* Maximum file size in MB / maxFileSizeMB: number; /* Maximum duration in seconds */ maxDurationSeconds?: number; };| Model limits | |vendorOptions?|vendorOptions?: Record<string, VendorOptionSchema>;` | Vendor-specific options schema |

STTOptions interface

📍 src/domain/interfaces/IAudioProvider.ts:115

Options for speech-to-text transcription

Properties
Property Type Description
model model: string; Model to use (e.g., 'whisper-1', 'gpt-4o-transcribe')
audio `audio: Buffer string;`
sampleRate? `sampleRate?: 8000 16000
encoding? `encoding?: 'pcm' 'mulaw'
language? language?: string; Language code (ISO-639-1), optional for auto-detection
outputFormat? outputFormat?: STTOutputFormat; Output format
includeTimestamps? includeTimestamps?: boolean; Include word/segment timestamps
timestampGranularity? `timestampGranularity?: 'word' 'segment';`
prompt? prompt?: string; Optional prompt to guide the model
temperature? temperature?: number; Temperature for sampling (0-1)
vendorOptions? vendorOptions?: Record&lt;string, unknown&gt;; Vendor-specific options passthrough

STTResponse interface

📍 src/domain/interfaces/IAudioProvider.ts:177

Response from speech-to-text transcription

Properties
Property Type Description
text text: string; Transcribed text
language? language?: string; Detected or specified language
durationSeconds? durationSeconds?: number; Audio duration in seconds
words? words?: WordTimestamp[]; Word-level timestamps (if requested)
segments? segments?: SegmentTimestamp[]; Segment-level timestamps (if requested)

STTOutputFormat type

📍 src/domain/entities/STTModel.ts:17

STT output format types

typescript
type STTOutputFormat = 'json' | 'text' | 'srt' | 'vtt' | 'verbose_json'

STTOutputFormat type

📍 src/domain/interfaces/IAudioProvider.ts:110

STT output format types

typescript
type STTOutputFormat = 'json' | 'text' | 'srt' | 'vtt' | 'verbose_json'

calculateSTTCost function

📍 src/domain/entities/STTModel.ts:633

Calculate estimated cost for STT

typescript
export function calculateSTTCost(
  modelName: string,
  durationSeconds: number,
  options?: { inputTokens?: number; streaming?: boolean }
): number | null

getSTTModelsWithFeature function

📍 src/domain/entities/STTModel.ts:622

Get STT models that support a specific feature

typescript
export function getSTTModelsWithFeature(
  feature: keyof ISTTModelDescription['capabilities']['features']
): ISTTModelDescription[]

STT_MODEL_REGISTRY const

📍 src/domain/entities/STTModel.ts:152

Complete STT model registry Last full audit: October 2026

Properties
Property Type Description
'gpt-transcribe' `{ 
name: 'gpt-transcribe',
displayName: 'GPT Transcribe',
provider: Vendor.OpenAI,
description: 'Current accurate file-transcription model for multilingual audio',
isActive: true,
lifecycle: 'active',
availability: 'public',
preferred: true,
endpoints: ['audio_transcription'],
releaseDate: '2026-07-09',
sources: {
  documentation: 'https://developers.openai.com/api/docs/models/gpt-transcribe',
  pricing: 'https://developers.openai.com/api/docs/pricing',
  lastVerified: '2026-08-30',
},
capabilities: {
  ...WHISPER_BASE_CAPABILITIES,
  outputFormats: ['json', 'text'],
  features: { translation: false, diarization: false, streaming: false, punctuation: true, profanityFilter: false },
  limits: { maxFileSizeMB: 25, maxDurationSeconds: 7200 },
},
pricing: { perMinute: 0.0045, currency: 'USD' },

}| - | |'gpt-4o-mini-transcribe'|{ name: 'gpt-4o-mini-transcribe', displayName: 'GPT-4o Mini Transcribe', provider: Vendor.OpenAI, description: 'Cost-efficient GPT-4o transcription for high-volume workloads', isActive: true, lifecycle: 'active', availability: 'public', endpoints: ['audio_transcription'], releaseDate: '2025-03-20', sources: { documentation: 'https://developers.openai.com/api/docs/models/gpt-4o-mini-transcribe', pricing: 'https://developers.openai.com/api/docs/pricing', lastVerified: '2026-08-30', }, capabilities: { ...WHISPER_BASE_CAPABILITIES, outputFormats: ['json', 'text'], features: { translation: false, diarization: false, streaming: false, punctuation: true, profanityFilter: false }, limits: { maxFileSizeMB: 25, maxDurationSeconds: 7200 }, }, pricing: { perMinute: 0.003, currency: 'USD' }, }| - | |'gpt-live-transcribe'|{ name: 'gpt-live-transcribe', displayName: 'GPT Live Transcribe', provider: Vendor.OpenAI, description: 'Recommended streaming speech-to-text model with incremental transcript deltas, vocabulary hints, multilingual hints, and tunable latency', isActive: true, sources: { documentation: 'https://developers.openai.com/api/docs/models/gpt-live-transcribe', pricing: 'https://developers.openai.com/api/docs/pricing', lastVerified: '2026-08-30', }, capabilities: { ...WHISPER_BASE_CAPABILITIES, outputFormats: ['json', 'text'], features: { translation: false, diarization: false, streaming: true, punctuation: true, profanityFilter: false, }, limits: { maxFileSizeMB: 0 }, vendorOptions: { delay: { type: 'string', description: 'Streaming transcript latency/accuracy tradeoff', default: 'low', }, keywords: { type: 'array', description: 'Literal vocabulary hints such as product names and acronyms', }, languages: { type: 'array', description: 'Expected ISO language codes; do not combine with language', }, }, }, pricing: { perMinute: 0.017, currency: 'USD' }, }| - | |'gpt-realtime-whisper'|{ name: 'gpt-realtime-whisper', displayName: 'GPT Realtime Whisper', provider: Vendor.OpenAI, description: 'Low-latency streaming speech-to-text model for realtime transcription', isActive: true, sources: { documentation: 'https://developers.openai.com/api/docs/models/gpt-realtime-whisper', pricing: 'https://developers.openai.com/api/docs/pricing', lastVerified: '2026-08-30', }, capabilities: { ...WHISPER_BASE_CAPABILITIES, outputFormats: ['json', 'text'], features: { translation: false, diarization: false, streaming: true, punctuation: true, profanityFilter: false, }, limits: { maxFileSizeMB: 0 }, }, pricing: { perMinute: 0.017, currency: 'USD' }, }| - | |'gpt-4o-transcribe'|{ name: 'gpt-4o-transcribe', displayName: 'GPT-4o Transcribe', provider: Vendor.OpenAI, description: 'GPT-4o based transcription with superior accuracy and context understanding', isActive: true, releaseDate: '2025-04-01', sources: { documentation: 'https://platform.openai.com/docs/guides/speech-to-text', pricing: 'https://openai.com/pricing', lastVerified: '2026-08-30', }, capabilities: { ...WHISPER_BASE_CAPABILITIES, features: { translation: true, diarization: false, streaming: false, // Not implementing streaming in v1 punctuation: true, profanityFilter: false, }, limits: { maxFileSizeMB: 25, maxDurationSeconds: 7200 }, }, pricing: { perMinute: 0.006, currency: 'USD' }, }| - | |'gpt-4o-transcribe-diarize'|{ name: 'gpt-4o-transcribe-diarize', displayName: 'GPT-4o Transcribe + Diarization', provider: Vendor.OpenAI, description: 'GPT-4o transcription with speaker identification', isActive: true, releaseDate: '2025-04-01', sources: { documentation: 'https://platform.openai.com/docs/guides/speech-to-text', pricing: 'https://openai.com/pricing', lastVerified: '2026-08-30', }, capabilities: { ...WHISPER_BASE_CAPABILITIES, outputFormats: ['json', 'verbose_json'], features: { translation: true, diarization: true, // Built-in speaker identification streaming: false, punctuation: true, profanityFilter: false, }, limits: { maxFileSizeMB: 25, maxDurationSeconds: 7200 }, vendorOptions: { max_speakers: { type: 'number', description: 'Maximum number of speakers to detect', min: 2, max: 10, default: 4, }, }, }, pricing: { perMinute: 0.012, currency: 'USD' }, // 2x for diarization }| - | |'whisper-1'|{ name: 'whisper-1', displayName: 'Whisper', provider: Vendor.OpenAI, description: "OpenAI's general-purpose speech recognition model", isActive: true, releaseDate: '2023-03-01', sources: { documentation: 'https://platform.openai.com/docs/guides/speech-to-text', pricing: 'https://openai.com/pricing', lastVerified: '2026-08-30', }, capabilities: { ...WHISPER_BASE_CAPABILITIES, inputFormats: ['mp3', 'mp4', 'mpeg', 'mpga', 'm4a', 'wav', 'webm'], features: { translation: true, diarization: false, streaming: false, punctuation: true, profanityFilter: false, }, limits: { maxFileSizeMB: 25 }, }, pricing: { perMinute: 0.006, currency: 'USD' }, }| - | |'gemini-3.5-transcribe'|{ name: 'gemini-3.5-transcribe', displayName: 'Gemini 3.5 Transcribe', provider: Vendor.Google, description: 'Dedicated file transcription with automatic language detection, diarization, word timestamps, and custom vocabulary', isActive: true, lifecycle: 'active', availability: 'public', preferred: true, endpoints: ['interactions'], releaseDate: '2026-08-26', sources: { documentation: 'https://ai.google.dev/gemini-api/docs/transcribe', pricing: 'https://ai.google.dev/gemini-api/docs/pricing', lastVerified: '2026-08-30', }, capabilities: { ...WHISPER_BASE_CAPABILITIES, inputFormats: ['wav', 'mp3', 'aiff', 'aac', 'ogg', 'flac'], outputFormats: ['text'], timestamps: { supported: true, granularities: ['word', 'segment'] }, features: { translation: false, diarization: true, streaming: false, punctuation: true, profanityFilter: false }, limits: { maxFileSizeMB: 20, maxDurationSeconds: 34_200 }, vendorOptions: { customVocabulary: { type: 'array', description: 'Up to 1,000 phrases to bias recognition toward' }, diarizationMode: { type: 'string', description: 'Set to speaker to identify up to eight speakers' }, transcriptionConfig: { type: 'object', description: 'Additional Gemini Interactions transcription_config fields' }, }, }, pricing: { perMinute: 0.005, perMInputTokens: 2, currency: 'USD' }, }| - | |'gemini-3.5-transcribe-live'|{ name: 'gemini-3.5-transcribe-live', displayName: 'Gemini 3.5 Transcribe Live', provider: Vendor.Google, description: 'Low-latency bidirectional WebSocket audio transcription', isActive: true, lifecycle: 'active', availability: 'public', endpoints: ['realtime'], releaseDate: '2026-08-26', sources: { documentation: 'https://ai.google.dev/gemini-api/docs/transcribe', pricing: 'https://ai.google.dev/gemini-api/docs/pricing', lastVerified: '2026-08-30', }, capabilities: { ...WHISPER_BASE_CAPABILITIES, inputFormats: ['pcm', 'wav'], outputFormats: ['text'], timestamps: { supported: true, granularities: ['word', 'segment'] }, features: { translation: false, diarization: true, streaming: true, punctuation: true, profanityFilter: false }, limits: { maxFileSizeMB: 0 }, }, pricing: { perMinute: 0.009, streamingPerMinute: 0.009, perMInputTokens: 3.5, currency: 'USD' }, }| - | |'gemini-3.6-flash'|{ name: 'gemini-3.6-flash', displayName: 'Gemini 3.6 Flash Audio Transcription', provider: Vendor.Google, description: 'Gemini Interactions transcription with language hints, normalized timestamps, diarization, and custom vocabulary', isActive: true, lifecycle: 'active', availability: 'public', endpoints: ['interactions'], releaseDate: '2026-07-21', sources: { documentation: 'https://ai.google.dev/gemini-api/docs/audio', pricing: 'https://ai.google.dev/gemini-api/docs/pricing', lastVerified: '2026-08-30', }, capabilities: { ...WHISPER_BASE_CAPABILITIES, inputFormats: ['wav', 'mp3', 'aiff', 'aac', 'ogg', 'flac'], outputFormats: ['text'], timestamps: { supported: true, granularities: ['segment'] }, features: { translation: true, diarization: true, streaming: false, punctuation: true, profanityFilter: false }, limits: { maxFileSizeMB: 20, maxDurationSeconds: 34200 }, vendorOptions: { instructions: { type: 'string', description: 'Custom transcription, translation, or extraction instructions' }, customVocabulary: { type: 'array', description: 'Phrases to bias native speech recognition toward' }, diarizationMode: { type: 'string', description: 'Set to speaker to include speaker labels on words' }, transcriptionConfig: { type: 'object', description: 'Additional Gemini Interactions transcription_config fields' }, }, }, pricing: { perMInputTokens: 1.5, currency: 'USD' }, }| - | |'grok-voice-transcribe-2.0'|{ name: 'grok-voice-transcribe-2.0', displayName: 'Grok Voice Transcribe 2.0', provider: Vendor.Grok, description: 'Current xAI file and streaming transcription model with timestamps, diarization, and multichannel support', isActive: true, lifecycle: 'active', availability: 'region_limited', preferred: true, endpoints: ['audio_transcription', 'realtime'], releaseDate: '2026-09-17', sources: { documentation: 'https://docs.x.ai/developers/model-capabilities/audio/speech-to-text', pricing: 'https://docs.x.ai/developers/models/speech-to-text', lastVerified: '2026-10-07' }, capabilities: { ...WHISPER_BASE_CAPABILITIES, outputFormats: ['json', 'text', 'verbose_json'], features: { translation: false, diarization: true, streaming: true, punctuation: true, profanityFilter: false }, limits: { maxFileSizeMB: 500 }, vendorOptions: { format: { type: 'boolean', description: 'Apply automatic transcript formatting', default: false }, multichannel: { type: 'boolean', description: 'Transcribe channels independently', default: false }, channels: { type: 'number', description: 'Number of channels in raw audio', min: 2, max: 8 }, diarize: { type: 'boolean', description: 'Identify distinct speakers', default: false }, keyterm: { type: 'array', description: 'Terms whose recognition should be boosted' }, filler_words: { type: 'boolean', description: 'Retain filler words in the transcript', default: false }, vad_threshold: { type: 'number', description: 'Voice-activity detection threshold', min: 0, max: 1, default: 0.08 }, }, }, pricing: { perMinute: 0.0016666667, streamingPerMinute: 0.0033333333, currency: 'USD' }, }| - | |'xai-stt'|{ name: 'xai-stt', displayName: 'xAI Speech to Text', provider: Vendor.Grok, description: 'Low-cost xAI file and streaming transcription with timestamps, diarization, and multichannel support', isActive: true, lifecycle: 'legacy', availability: 'region_limited', replacementModel: 'grok-voice-transcribe-2.0', endpoints: ['audio_transcription', 'realtime'], releaseDate: '2026-07-23', sources: { documentation: 'https://docs.x.ai/developers/model-capabilities/audio/speech-to-text', pricing: 'https://docs.x.ai/developers/models/speech-to-text', lastVerified: '2026-08-30', }, capabilities: { ...WHISPER_BASE_CAPABILITIES, outputFormats: ['json', 'text', 'verbose_json'], features: { translation: false, diarization: true, streaming: true, punctuation: true, profanityFilter: false }, limits: { maxFileSizeMB: 500 }, vendorOptions: { format: { type: 'boolean', description: 'Apply automatic transcript formatting', default: false }, multichannel: { type: 'boolean', description: 'Transcribe channels independently', default: false }, channels: { type: 'number', description: 'Number of channels in raw audio', min: 2, max: 8 }, diarize: { type: 'boolean', description: 'Identify distinct speakers', default: false }, keyterm: { type: 'array', description: 'Terms whose recognition should be boosted' }, filler_words: { type: 'boolean', description: 'Retain filler words in the transcript', default: false }, vad_threshold: { type: 'number', description: 'Voice-activity detection threshold', min: 0, max: 1, default: 0.08 }, }, }, pricing: { perMinute: 0.0016666667, streamingPerMinute: 0.0033333333, currency: 'USD' }, }| - | |'whisper-large-v3'|{ name: 'whisper-large-v3', displayName: 'Whisper Large v3 (Groq)', provider: Vendor.Groq, description: 'Ultra-fast Whisper on Groq LPUs - 12x cheaper than OpenAI', isActive: true, releaseDate: '2024-04-01', sources: { documentation: 'https://console.groq.com/docs/speech-to-text', pricing: 'https://console.groq.com/docs/speech-to-text', lastVerified: '2026-08-30', }, capabilities: { ...WHISPER_BASE_CAPABILITIES, timestamps: { supported: true, granularities: ['word', 'segment'] }, outputFormats: ['json', 'text', 'verbose_json'], features: { translation: true, diarization: false, streaming: false, punctuation: true, profanityFilter: false, }, limits: { maxFileSizeMB: 100 }, }, pricing: { perMinute: 0.00185, currency: 'USD' }, }| - | |'whisper-large-v3-turbo'|{ name: 'whisper-large-v3-turbo', displayName: 'Whisper Large v3 Turbo (Groq)', provider: Vendor.Groq, description: 'Cost-optimized multilingual Whisper transcription on Groq LPUs', isActive: true, lifecycle: 'active', availability: 'public', preferred: true, releaseDate: '2024-09-18', sources: { documentation: 'https://console.groq.com/docs/speech-to-text', pricing: 'https://console.groq.com/docs/speech-to-text', lastVerified: '2026-08-30', }, capabilities: { ...WHISPER_BASE_CAPABILITIES, outputFormats: ['json', 'text', 'verbose_json'], timestamps: { supported: true, granularities: ['word', 'segment'] }, features: { translation: true, diarization: false, streaming: false, punctuation: true, profanityFilter: false }, limits: { maxFileSizeMB: 100 }, }, pricing: { perMinute: 0.0006666667, currency: 'USD' }, }| - | |'distil-whisper-large-v3-en'|{ name: 'distil-whisper-large-v3-en', displayName: 'Distil Whisper (Groq)', provider: Vendor.Groq, description: 'Faster English-only Whisper variant on Groq', isActive: false, lifecycle: 'retired', retirementDate: '2025-08-23', replacementModel: 'whisper-large-v3-turbo', releaseDate: '2024-04-01', sources: { documentation: 'https://console.groq.com/docs/speech-to-text', pricing: 'https://console.groq.com/docs/speech-to-text', lastVerified: '2026-08-30', }, capabilities: { inputFormats: AUDIO_FORMATS.STT_INPUT, outputFormats: ['json', 'text', 'verbose_json'], languages: ['en'], // English only timestamps: { supported: true, granularities: ['segment'] }, features: { translation: false, diarization: false, streaming: false, punctuation: true, profanityFilter: false, }, limits: { maxFileSizeMB: 25 }, }, pricing: { perMinute: 0.00033, currency: 'USD' }, }` | - |

Documentation snapshot · 2026-11-02Suggest a correction ↗

Search documentation

Type to search the v2 documentation.

↑ ↓ to navigate Esc to close