Innov8by Alex Tom
Suggest free access
Back to free access

Whisper Large V3 Turbo

2 free access methods

Groq

API

20 requests/min, 2,000 requests/day, 7,200 audio seconds/hour, 28,800 audio seconds/day.

Reset · Provider minute, hour (audio where applicable), and day windows. See the account Limits page for actual limits and the response headers for retry/reset timing.

Get API access
Setup, evidence & eligibility

Limits are enforced at the organization level; Groq directs users to account settings for exact limits. Free-tier files are capped at 25 MB.

How to use it

  1. Sign in to GroqCloud, create a key under API Keys, and check your organization’s Free Plan limits.
  2. Use the exact model ID listed below.
  3. Create a Groq API key on the Free plan.
  4. Send a supported audio file up to 25 MB to the audio transcription endpoint using whisper-large-v3-turbo.
  5. Check your current organization limits in GroqCloud.
Model ID
whisper-large-v3-turbo
Endpoint
https://api.groq.com/openai/v1/audio/transcriptions
Protocol
OpenAI-compatible REST with a Groq API key

Checks & requirements

Listing status
Documented
Source checked
Nov 18, 2026
Hands-on tested
Not recorded
Account checked
Not recorded
Generation tested
Not recorded
Account
Required
Payment card
Unknown
Phone
Unknown
Regions
Free-plan availability in India has not been verified.
India access
Unknown
Watermark
Not applicable
Commercial use
Unknown
Privacy
Groq generally does not retain standard inference inputs or outputs. Reliability and abuse review can trigger temporary logging. See Data Controls.
  • Groq Free Plan limits Provider documentation · Checked Nov 18, 2026

    The named Free Plan row lists 20 requests/min, 2,000 requests/day, 7,200 audio seconds/hour, 28,800 audio seconds/day, subject to organization-level exceptions.

  • Groq model and usage docs Provider documentation · Checked Nov 18, 2026

    Transcribe multilingual audio using the faster Whisper Large V3 variant.

  • Groq API quickstart Provider documentation · Checked Nov 18, 2026

    Create a GroqCloud API key for authenticated API requests.

  • Groq data controls Provider documentation · Checked Nov 18, 2026

    Default inference does not retain inputs or outputs, with exceptions for reliability, abuse monitoring and stateful features.

  • Free Inference source snapshot Directory report · Checked Nov 18, 2026

    Groq was identified by Free Inference. Exact availability and quota come from Groq's current Free Plan table.

  • Groq Cloud platform Provider documentation · Checked Nov 18, 2026

    Groq's product page links to its official hosted inference platform.

Provider setup guide

Workers AI

API · Cloudflare

10,000 shared Neurons/day. This model uses 46.63 neurons per audio minute.

Reset · Daily at 00:00 UTC.

Get API access
Setup, evidence & eligibility

Every model draws from the same daily balance. Requests fail once it runs out on Workers Free. The debit depends on the units used in the request.

How to use it

  1. Open Workers AI in your Cloudflare account, select Use REST API, then create a Workers AI API token and copy your account ID.
  2. Use the exact model ID listed below.
  3. Use a Cloudflare Workers Free account and create a Workers AI API token.
  4. POST to the Workers AI run endpoint for @cf/openai/whisper-large-v3-turbo with the account ID, bearer token and the model's documented request body.
  5. Monitor the shared Neuron balance in the Workers AI dashboard.
Model ID
@cf/openai/whisper-large-v3-turbo
Endpoint
https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run/@cf/openai/whisper-large-v3-turbo
Protocol
Cloudflare Workers AI REST with a bearer token

Checks & requirements

Listing status
Documented
Source checked
Nov 18, 2026
Hands-on tested
Not recorded
Account checked
Not recorded
Generation tested
Not recorded
Account
Required
Payment card
Unknown
Phone
Unknown
Regions
Free-plan availability in India has not been verified.
India access
Unknown
Watermark
Not applicable
Commercial use
Unknown
Privacy
Cloudflare does not train models on Workers AI customer content. Standard stateless inference is subject to Cloudflare's published retention exceptions.
  • Workers AI model pricing Provider documentation · Checked Nov 18, 2026

    Cloudflare's exact @cf/openai/whisper-large-v3-turbo pricing row measures Neurons as 46.63 neurons per audio minute.

  • Workers AI free allocation Provider documentation · Checked Nov 18, 2026

    Workers Free provides 10,000 shared Neurons daily, resetting at 00:00 UTC. The pricing page lists separate paid-only model exceptions.

  • Workers AI Models catalog Provider documentation · Checked Nov 18, 2026

    Cloudflare's listed model supports this task. Use the Whisper Large V3 Turbo model for automatic transcription.

  • Workers AI REST quickstart Provider documentation · Checked Nov 18, 2026

    Workers AI accepts an authenticated REST request for the exact model using a Workers AI API token and account ID.

  • Workers AI data usage Provider documentation · Checked Nov 18, 2026

    Cloudflare does not use Workers AI customer content to train AI models and describes retention exceptions for stateful features.

  • Free Inference source snapshot Directory report · Checked Nov 18, 2026

    Free Inference's Cloudflare coverage was a discovery lead; the exact model was identified from Cloudflare.

  • Cloudflare API reference Provider documentation · Checked Nov 18, 2026

    Cloudflare's API origin routes to its API reference.

  • Cloudflare model documentation Provider documentation · Checked Nov 18, 2026

    Cloudflare lists model ID @cf/openai/whisper-large-v3-turbo on the individual model page with a Workers AI request example or schema.

Provider setup guide