Granite Speech 3.3 8B is IBM's speech to text model, starting at $4.90 / 1M output. A speech-to-text transcription model built on the Granite architecture for automatic speech recognition.
Specifications
Canonical IDibm-granite-speech-3-3-8b
TypeSpeech to Text
StatusActive
CreatorIBMIBM
Providers
Input ModalitiesAudio
Output ModalitiesText
Parameters8B

Capabilities

Input1/5
Text·
Image·
Audio✓
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Output
$ / 1M
Replicate logo
Replicate
replicate/ibm-granite/granite-speech-3.3-8b
$4.90

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host Granite Speech 3.3 8B, ranked by cheapest on-demand price. The model needs about 19 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
g2-standard-4GCPnvidia-l424 GB$0.705/hr
g6.xlargeAWSL422 GB$0.805/hr
g2-standard-8GCPnvidia-l424 GB$0.851/hr
7 more instances can run Granite Speech 3.3 8B
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Granite 4.2 8B131K$0.060$0.150Available
Granite 4.1 8B131K$0.050$0.100Deprecated
Granite 4 Micro H131K——Available
Granite 4.2 30B—131K——Available
Granite 4.2 3B—131K——Available
Granite 4 350M————Available
Granite 4 350M H————Available
Granite 4 H Micro————Available
Granite 4 H Small————Available
Granite 4 H Tiny————Available
Granite Speech 3.3 8B———$4.90Current

Model IDs

ibm-granite-speech-3-3-8b
replicate/ibm-granite/granite-speech-3.3-8b