Deepgram Whisper Small API: Endpoint & 30% Discount
Transcribe speech with Deepgram Whisper Small on LLM.API—batch or streaming audio to text with the same developer surface as your other models.
What is Deepgram Whisper Small?
With Deepgram Whisper Small, LLM.API turns audio into text for product voice features. Speech-to-text model by Deepgram. The model id `whisper-small` keeps STT alongside your other endpoints.
Can you self-host Deepgram Whisper Small?
No. We found no public weights for Deepgram Whisper Small on Hugging Face, so there is nothing to download, quantize or serve on your own GPUs: no VRAM budget, no vLLM or GGUF build to plan for. The only way to run it is over an API.
Not on LLM.API yet
We do not route this model through our API at the moment. Browse the models you can call today — most workloads have a close match already live.
Providers
LLM.API routes Deepgram Whisper Small to the providers below, with discounted effective rates versus list price.
List price by provider
InputOutputProvider list prices; the LLM.API discount applies on top.
| Provider | Pricing | Context | Capabilities |
|---|---|---|---|
| in $0; out — per minute of audio | — | — |
Prices and availability from the LLMAPI catalogue, updated nightly. Last updated 24 Sept 2026.
Try this model
Test Deepgram Whisper Small right here — free to start.
Suggestions for your first prompt
Not available on LLM API yet
We do not route this model through our API at the moment, so there is no endpoint or code snippet for it yet. Browse the models you can call today — most workloads have a close match already live.
Browse available modelsDeepgram Whisper Small in production
What the model is good at.
Speech transcription
Converts spoken audio into text for captions, notes, and search. Tuned to how teams typically call Deepgram Whisper Small.
Voice UX input
Powers voice-driven product interfaces and IVR handoffs. Reflects speech-to-text positioning for this endpoint.
Caption generation
Produces base transcripts for subtitle workflows. Relevant for `whisper-small` workloads on LLM.API.
Multilingual audio
Handles diverse accents and languages depending on the model. Grounded in the model's stt role rather than generic chat claims.
Compliance archives
Creates text records of spoken interactions for audit trails. Grounded in the model's stt role rather than generic chat claims.
What you get when you call Deepgram Whisper Small through LLM.API.
Unified AI Routing
Production: Reach Deepgram Whisper Small and sibling models through one OpenAI-compatible endpoint.
One endpoint, every model.Cost Control
Production: Compare provider price points and keep spend visible as you scale Deepgram Whisper Small.
More performance, less spend.Reliability Layer
Retry and route across configured providers when a single upstream blips.
Never go dark on users.Observability
Production: Trace prompts, tokens, and errors for Deepgram Whisper Small alongside the rest of your stack.
See every token, everywhere.Drop-in SDKs
Keep using familiar OpenAI client patterns with base URL https://api.llmapi.ai/v1.
Think tasks, not models.Model Breadth
Production: Swap Deepgram Whisper Small for chat, media, or embedding alternatives without rewriting auth.
Scale from 1 to millions.
When to Use — When NOT to Use
Use it if...
- You need speech-to-text for batch or streaming audio (Deepgram Whisper Small)
- Voice is a primary input modality in your product (Deepgram Whisper Small)
- You will pipe transcripts into search or LLM summarization (Deepgram Whisper Small)
Avoid if...
- You need text-to-speech or chat generation instead of transcription
- You require guaranteed perfect transcripts for every accent without evaluation
- Your audio cannot leave your compliance boundary and you lack an approved provider path
COMMUNITY
What developers say about speech-to-text models
Summarised from publicly published developer and community reviews of this model family. Opinions are the sources’, not LLM.API’s, and may not be specific to Deepgram Whisper Small.
- Head-to-head tests of the leading APIs land within a point or two of each other; the choice usually comes down to language coverage, streaming latency and batch pricing.
- Voice-agent developers report streaming latency and endpointing quality matter more in production than headline word-error rates.
- Whisper-family models remain the default open baseline, with hosted providers winning on real-time features and diarization.
SOURCES
Frequently Asked Questions
What are limitations of Deepgram Whisper Small?
Like other API models, Deepgram Whisper Small can be wrong, incomplete, or uneven on edge cases. Validate outputs for high-stakes use. Media/OCR/STT models additionally depend on input quality.
Does Deepgram Whisper Small support streaming?
Streaming depends on the active provider; check the providers table on this page for flags.
Which providers serve Deepgram Whisper Small?
LLM.API currently lists: deepgram. Availability can vary by region and account.
Does Deepgram Whisper Small translate speech?
Primary behavior is transcription to text. Translation—if needed—should be a separate step with a chat model unless the provider explicitly offers it.
What modalities does Deepgram Whisper Small support?
Deepgram Whisper Small accepts audio and produces text according to its architecture metadata on LLM.API.
Can I use tools or structured outputs with Deepgram Whisper Small?
Tooling support varies; for pure stt models, prefer the modalities listed rather than assuming chat tools.
What is Deepgram Whisper Small?
Speech-to-text model by Deepgram. On LLM.API it is addressed as `whisper-small`.
Is Deepgram Whisper Small a chat model?
No—Deepgram Whisper Small is categorized as a stt model. Use the matching API surface rather than assuming chat completions.
When should I choose Deepgram Whisper Small?
You need speech-to-text for batch or streaming audio — especially when you specifically need Deepgram Whisper Small.
COMPARE
Competitive Models
Deepgram Whisper Large
Input$0.0048$0.0034 / minuteList price per minute of audio, 30% LLM API discount applied.
$0.0048 in / — out per minute of audio, context varies — the closest current alternative to Deepgram Whisper Small.
Deepgram Nova 3 Multilingual
Input$0.0052$0.0036 / minuteList price per minute of audio, 30% LLM API discount applied.
$0.0052 in / — out per minute of audio, context varies — the closest current alternative to Deepgram Whisper Small.
ElevenLabs Scribe v2
Input$0.0037$0.0026 / minuteList price per minute of audio, 30% LLM API discount applied.
$0.0037 in / — out per minute of audio, context varies — the closest current alternative to Deepgram Whisper Small.
Get one key to every model
Swap your API key. Keep your code.