# Free Hosted Whisper API Endpoints & Rate Limits

> 3 providers · 5 free models · Last updated: 12 Nov 2026

## Quick Answer

5 free Hosted Whisper API models across 3 providers including Groq, Cloudflare Workers AI, and NVIDIA NIM. Verified rate limits, context windows, and OpenAI-compatible endpoints. Last updated: 12 Nov 2026.

Free hosted OpenAI Whisper API endpoints for high-throughput speech transcription, including Groq (Whisper Large v3 & Turbo at 2,000 RPD) and Cloudflare Workers AI with zero credit card.

## Quick Connect

Fastest hosted Whisper Large v3 Turbo transcription endpoint.

- **Base URL:** `https://api.groq.com/openai/v1`
- **Model:** `whisper-large-v3-turbo`
- **Provider:** [Groq](/providers/groq/)

### Python (OpenAI SDK)

```python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.groq.com/openai/v1",
    api_key="your-api-key",  # from Groq
)

response = client.chat.completions.create(
    model="whisper-large-v3-turbo",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
```

### cURL (Terminal / Shell)

```bash
curl -X POST "https://api.groq.com/openai/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $API_KEY" \
  -d '{
    "model": "whisper-large-v3-turbo",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
```

## Rate Limits & Model Inventory

| Model | Provider | Cost | Context | RPM | TPM | RPD | Day tokens | Verified |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| whisper-large-v3-turbo | [Groq](/providers/groq/) | $0 | 25MB audio | 20 | 7.2K ASH (Audio sec/hr) | 2,000 | 28.8K ASD (8h audio/day) | 2026-11-12 |
| whisper-large-v3 | [Groq](/providers/groq/) | $0 | 25MB audio | 20 | 7.2K ASH (Audio sec/hr) | 2,000 | 28.8K ASD (8h audio/day) | 2026-11-12 |
| ~80 free models (Llama 3.x/4, Qwen, Gemma, DeepSeek-R1 distills, FLUX, Whisper, BGE embeddings) | [Cloudflare Workers AI](/providers/cloudflare-workers-ai/) | $0 | 8K-128K+ (model-dependent) | 300 text gen (720-1,500 other tasks) | Model-dependent | Not published | 10,000 neurons/day | 2026-11-12 |
| @cf/openai/whisper | [Cloudflare Workers AI](/providers/cloudflare-workers-ai/) | $0 | 25MB audio | 300 | Model-dependent | Not published | 10,000 neurons/day | 2026-11-12 |
| Whisper Large v3 | [NVIDIA NIM (build.nvidia.com)](/providers/nvidia-nim--build-nvidia-com/) | $0 | 448 | ~40 | Not published | Not published | ~1,000 credits at signup (up to ~5,000) | 2026-11-12 |

Web page: https://freeinference.dev/free-whisper-api/
Machine-readable JSON: /data/providers.json
Agent summary: /llms.txt

Numbers cross-checked against official docs and live probes as of 2026-11-12. Limits change without notice — this is a map, not a contract.