Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Inworld AI / STT

Inworld STT 1

Native multilingual speech recognition with live turn detection, optional voice-characteristic estimates and experimental word-level speaker attribution.

availableClosed weightsSpeech-to-text
Official documentation (opens in a new tab)Reviewed 13 Oct 2026
11 of 23 specification fields collected
File upload limitSync approximately 16 MB; async up to 512 MBSee specification notes below
Transcription outputTextSee specification notes below
Input billingSee ratesInworld API
Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum output
Not collected
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected
Parameters
Not collected
Architecture
Not collected
Languages
View all 30 entries
  • Arabic (ar)
  • Cantonese (yue)
  • Chinese (zh)
  • Czech (cs)
  • Danish (da)
  • Dutch (nl)
  • English (en)
  • Filipino (fil)
  • Finnish (fi)
  • French (fr)
  • German (de)
  • Greek (el)
  • Hindi (hi)
  • Hungarian (hu)
  • Indonesian (id)
  • Italian (it)
  • Japanese (ja)
  • Korean (ko)
  • Macedonian (mk)
  • Malay (ms)
  • Persian (fa)
  • Polish (pl)
  • Portuguese (pt)
  • Romanian (ro)
  • Russian (ru)
  • Spanish (es)
  • Swedish (sv)
  • Thai (th)
  • Turkish (tr)
  • Vietnamese (vi)
Source for Languages (opens in a new tab)
Context caching
Not collected
Maximum audio file
Sync approximately 16 MB; async up to 512 MBSource for Maximum audio file (opens in a new tab)

These are upload limits, not fixed audio-duration limits. The async guide states 512 MB; WebSocket sends audio incrementally.

Audio formats
LINEAR16 / WAV, MP3, OGG_OPUS, FLAC, AUTO_DETECT, Video: MP4/MOV/M4V, WEBM/MKV, MXFSource for Audio formats (opens in a new tab)

File routes extract audio from video; no visual understanding is implied. Audio-only M4A uses AUTO_DETECT, not MP4. WebSocket accepts LINEAR16 only.

Audio sample rates
16 kHz, 16-bit mono recommended; container sample rate can be detectedSource for Audio sample rates (opens in a new tab)
Output formats
JSON transcript, Optional word timestamps, Optional voice-profile estimatesSource for Output formats (opens in a new tab)
Speaker attribution
Experimental diarization on WebSocket and async; enable word timestamps and speaker diarization togetherSource for Speaker attribution (opens in a new tab)

IDs are scoped to one stream/job. Word confidence is unpopulated: omitted in async, zero in sync/stream. A zero is not measured recognition confidence.

Audio controls
Automatic end-of-turn detection or client-controlled turns; optional estimates of age, emotion, pitch, vocal style and accentSource for Audio controls (opens in a new tab)

Voice-profile labels are model estimates, not verified personal characteristics.

Published price
On-Demand $0.15 per audio hour; paid published plans $0.10 per audio hourSource for Published price (opens in a new tab)

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

API model ID
inworld/inworld-stt-1
Access
Native STT 1 access with modelId inworld/inworld-stt-1; account plan limits apply.
Regions
General API region not pinned by these contracts. EU and India residency are enterprise offerings, not assumed for every request.
API endpoint URL
https://api.inworld.ai/stt/v1/transcribeSource for API endpoint URL (opens in a new tab)
Required request fields
Base64 audio inside audioData.content and transcribeConfigSource for Required request fields (opens in a new tab)
Maximum audio file
Approximately 16 MBSource for Maximum audio file (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech recognitionTranscription · On-Demand1$0.15audio hour
Speech recognitionTranscription · Creator2$0.10audio hour
SubscriptionPlan fee · Creator3$25.00month
Speech recognitionTranscription · Builder4$0.10audio hour
SubscriptionPlan fee · Builder5$100.00month
Speech recognitionTranscription · Developer6$0.10audio hour
SubscriptionPlan fee · Developer7$300.00month
Speech recognitionTranscription · Growth8$0.10audio hour
SubscriptionPlan fee · Growth9$1,500.00month

Rate conditions

  1. On-Demand plan: pay as you go after included trial credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. Audio duration billing; no text-token or batch discount assumed. Taxes, custom enterprise terms and optional add-ons are separate.
  2. Creator plan costs $25/month and includes $25 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. Audio duration billing; no text-token or batch discount assumed. Taxes, custom enterprise terms and optional add-ons are separate.
  3. Monthly subscription includes $25 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
  4. Builder plan costs $100/month and includes $100 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. Audio duration billing; no text-token or batch discount assumed. Taxes, custom enterprise terms and optional add-ons are separate.
  5. Monthly subscription includes $100 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
  6. Developer plan costs $300/month and includes $300 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. Audio duration billing; no text-token or batch discount assumed. Taxes, custom enterprise terms and optional add-ons are separate.
  7. Monthly subscription includes $300 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
  8. Growth plan costs $1500/month and includes $1500 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. Audio duration billing; no text-token or batch discount assumed. Taxes, custom enterprise terms and optional add-ons are separate.
  9. Monthly subscription includes $1500 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
Pricing source (opens in a new tab)

Data & enterprise terms

The STT policy states sync/WebSocket audio and transcripts are processed in memory and redacted after processing; usage metadata remains. It states STT audio is not used for training. General ZDR controls and account entitlement still need workspace-specific confirmation.

Read the service policy (opens in a new tab)
API model ID
inworld/inworld-stt-1
Access
Native STT 1 access with modelId inworld/inworld-stt-1; account plan limits apply.
Regions
General API region not pinned by these contracts. EU and India residency are enterprise offerings, not assumed for every request.
API endpoint URL
wss://api.inworld.ai/stt/v1/transcribe:streamBidirectionalSource for API endpoint URL (opens in a new tab)
Required request fields
LINEAR16 streaming audio. Other container/compressed encodings are unsupported on WebSocket.Source for Required request fields (opens in a new tab)
Request quotas
Streaming concurrency: 10 / 20 / 100 / 300 / 1,000 by plan; enterprise customSource for Request quotas (opens in a new tab)
Generation controls
Up to 100 custom vocabulary prompts; character restrictions apply. inactivityTimeoutSeconds is not applied to STT 1, so use a client idle timerSource for Generation controls (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech recognitionTranscription · On-Demand1$0.15audio hour
Speech recognitionTranscription · Creator2$0.10audio hour
SubscriptionPlan fee · Creator3$25.00month
Speech recognitionTranscription · Builder4$0.10audio hour
SubscriptionPlan fee · Builder5$100.00month
Speech recognitionTranscription · Developer6$0.10audio hour
SubscriptionPlan fee · Developer7$300.00month
Speech recognitionTranscription · Growth8$0.10audio hour
SubscriptionPlan fee · Growth9$1,500.00month

Rate conditions

  1. On-Demand plan: pay as you go after included trial credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. Audio duration billing; no text-token or batch discount assumed. Taxes, custom enterprise terms and optional add-ons are separate.
  2. Creator plan costs $25/month and includes $25 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. Audio duration billing; no text-token or batch discount assumed. Taxes, custom enterprise terms and optional add-ons are separate.
  3. Monthly subscription includes $25 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
  4. Builder plan costs $100/month and includes $100 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. Audio duration billing; no text-token or batch discount assumed. Taxes, custom enterprise terms and optional add-ons are separate.
  5. Monthly subscription includes $100 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
  6. Developer plan costs $300/month and includes $300 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. Audio duration billing; no text-token or batch discount assumed. Taxes, custom enterprise terms and optional add-ons are separate.
  7. Monthly subscription includes $300 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
  8. Growth plan costs $1500/month and includes $1500 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. Audio duration billing; no text-token or batch discount assumed. Taxes, custom enterprise terms and optional add-ons are separate.
  9. Monthly subscription includes $1500 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
Pricing source (opens in a new tab)

Data & enterprise terms

The STT policy states sync/WebSocket audio and transcripts are processed in memory and redacted after processing; usage metadata remains. It states STT audio is not used for training. General ZDR controls and account entitlement still need workspace-specific confirmation.

Read the service policy (opens in a new tab)
API model ID
inworld/inworld-stt-1
Access
Native STT 1 access with modelId inworld/inworld-stt-1; account plan limits apply.
Regions
General API region not pinned by these contracts. EU and India residency are enterprise offerings, not assumed for every request.
API endpoint URL
https://api.inworld.ai/stt/v1/transcribe:asyncSource for API endpoint URL (opens in a new tab)
Required request fields
Base64 JSON, multipart with config before file, or direct HTTPS audioUri; fetch timeout five minutesSource for Required request fields (opens in a new tab)
Data retention
Submitted audio and transcript retained seven days; signed result URL is not renewed by pollingSource for Data retention (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech recognitionTranscription · On-Demand1$0.15audio hour
Speech recognitionTranscription · Creator2$0.10audio hour
SubscriptionPlan fee · Creator3$25.00month
Speech recognitionTranscription · Builder4$0.10audio hour
SubscriptionPlan fee · Builder5$100.00month
Speech recognitionTranscription · Developer6$0.10audio hour
SubscriptionPlan fee · Developer7$300.00month
Speech recognitionTranscription · Growth8$0.10audio hour
SubscriptionPlan fee · Growth9$1,500.00month

Rate conditions

  1. On-Demand plan: pay as you go after included trial credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. Audio duration billing; no text-token or batch discount assumed. Taxes, custom enterprise terms and optional add-ons are separate.
  2. Creator plan costs $25/month and includes $25 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. Audio duration billing; no text-token or batch discount assumed. Taxes, custom enterprise terms and optional add-ons are separate.
  3. Monthly subscription includes $25 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
  4. Builder plan costs $100/month and includes $100 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. Audio duration billing; no text-token or batch discount assumed. Taxes, custom enterprise terms and optional add-ons are separate.
  5. Monthly subscription includes $100 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
  6. Developer plan costs $300/month and includes $300 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. Audio duration billing; no text-token or batch discount assumed. Taxes, custom enterprise terms and optional add-ons are separate.
  7. Monthly subscription includes $300 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
  8. Growth plan costs $1500/month and includes $1500 in shared product credits. Usage consumes credits at this plan rate; subscription fee is not an additional charge per request. Monthly credits roll over for up to three months under plan conditions; purchased top-ups expire after one year. Audio duration billing; no text-token or batch discount assumed. Taxes, custom enterprise terms and optional add-ons are separate.
  9. Monthly subscription includes $1500 shared credits consumed at the plan’s unit rates. Annual subscriptions and custom agreements are separate. Do not add this full fee to each synthesis.
Pricing source (opens in a new tab)

Data & enterprise terms

The async guide explicitly stores submitted audio and transcript for seven days. The ZDR guide’s sync/WebSocket in-memory claims are not automatically transferred to async jobs. No blanket async zero-retention guarantee is established.

Read the service policy (opens in a new tab)

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Inworld API

inworld/inworld-stt-1
Not verified

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

How it works
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

How to enable it
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Usage fields
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Billing rules
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Inworld API

inworld/inworld-stt-1
Not verified

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

How it works
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

How to enable it
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Usage fields
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Billing rules
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Inworld API

inworld/inworld-stt-1
Not verified

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

How it works
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

How to enable it
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Usage fields
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Billing rules
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache mechanism, lifetime or cached-token price established. Free synthesisContext text and reusable voice profiles do not establish prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Inworld grants limited service/model access and reserves model IP under its proprietary terms, including separately contracted customer-hosted deployment. The TTS-1 research release publishes training/modeling code, not the production TTS model weights. Current TTS/STT release identities are established in the native catalog; routed third-party models are excluded.

Classification evidence (opens in a new tab)

Sources reviewed