Speech-to-text model from OpenAI. One API key reaches this provider and every other model in the catalog.
No card required. Start with 1 million free tokens.
About Whisper Large V3
Whisper Large V3 is a speech-to-text model published by OpenAI. Through TrustedRouter it runs on 1 provider, from $0.017392/audio minute. One provider offers zero data retention, and Privatemode also runs it in a confidential enclave.
- Model ID
openai/whisper-large-v3- Publisher
- OpenAI
- Input limit
- 7 MiB, up to 10 minutes
- Input formats
- mp3, wav
- Billing
- audio seconds
- Price
- $0.017392/audio minute
- Modes
- transcription
- Billing
- Credits
Set it up with your agent
Paste this into Claude Code, Cursor or any coding agent.
Use Whisper Large V3 through TrustedRouter in this project.
1. Read https://trustedrouter.com/llms.txt
2. Point the OpenAI-compatible client at
https://api.trustedrouter.com/v1 and read the key from
TRUSTEDROUTER_API_KEY.
3. Set the model to openai/whisper-large-v3.
4. Run the tests, then show me the diff before committing.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.trustedrouter.com/v1",
api_key=os.environ["TRUSTEDROUTER_API_KEY"],
)
with open("recording.wav", "rb") as audio:
response = client.audio.transcriptions.create(
model="openai/whisper-large-v3",
file=audio,
response_format="json",
)
print(response.text)
curl https://api.trustedrouter.com/v1/audio/transcriptions \
-H "Authorization: Bearer $TRUSTEDROUTER_API_KEY" \
-F model="openai/whisper-large-v3" \
-F file="@recording.wav"
Providers
Audio requests use the listed model and provider. These routes do not silently switch models or providers. Open a row for retention, location and weight format, or see how we check privacy claims and the live speed leaderboard.
| Provider | Price | Output | Details |
|---|---|---|---|
|
|
$0.017392/audio minute | Included | |
|
Retention Confidential compute with end-to-end encryption and zero data retention. Requests and responses are encrypted between TrustedRouter's enclave and release-pinned Privatemode workloads after attestation verification. Verification failures reject the request; there is no plaintext fallback. Privatemode explicitly states that prompts and responses are not stored after a request completes and are not used for training. Transient inference state may remain in a salt-isolated, in-memory prompt cache inside confidential workers until eviction. Operational metadata is retained for up to 90 days; per-key token usage is retained permanently for billing. Cache-routing metadata is visible to the provider edge. ZDR describes prompt/output retention, not metadata. Location Operator country: DE Headquarters / registered office: Not verified. Inference: EU-hosted inference, provider-declared; country and individual worker location unspecified. Privatemode declares EU hosting for its inference service. This does not establish an individual worker's country. Region pinning through TR: Not supported by the current TrustedRouter integration. Reviewed 2026-09-27. Weight format Unknown Price and speed Input $0.017392/audio minute · Cached input Not applicable · Output Included TTFT: insufficient data Speed: insufficient data |
|||
How to use Whisper Large V3
File transcription, billed per request or audio duration, not text tokens.
- Input
- POST /v1/audio/transcriptions with multipart file or base64 input_audio, and model. PCM WAV or MP3, at most 7 MiB and ten minutes.
- Output
- JSON text and usage; verbose_json adds supported timestamps.
Example input
{"model":"openai/whisper-large-v3","input_audio":{"data":"<base64>","format":"wav"}}
Example output
{"text":"Hello","usage":{"seconds":1,"cost":0.01}}
Questions
What model ID should I use for Whisper Large V3?
Use openai/whisper-large-v3 as the model field with the TrustedRouter OpenAI-compatible API. Credits routing and provider fallback happen behind that model ID.
Do you log my prompts or outputs?
No. Prompt and output content are intentionally excluded from the control plane and metadata systems. Optional content export requires explicit destination-level configuration.
Which providers serve Whisper Large V3?
TrustedRouter currently lists Privatemode for Whisper Large V3. Provider availability and routing eligibility can change as catalog and health data update.
How much does Whisper Large V3 cost through TrustedRouter?
The current Credits price is $0.017392/audio minute. Output is included; these are audio prices, not text-token prices.
How do I require zero data retention for Whisper Large V3?
Set provider.min_privacy to zdr on the request. TrustedRouter considers only routes with a recorded zero-data-retention posture and fails closed if no eligible route remains.
Whisper Large V3 vs other models
Start building with Whisper Large V3.
No card required. Start with 1 million free tokens.
