Capabilities
Explore what Gemini 3 Flash supports, then use the API section for a request tailored to this model.
Languages
Model Information
- Provider
- Google Gemini
- Product
- Speech-to-Text
- Release Date
- Dec 17, 2025
- Data Policy
- Configurable
- Region
- Global
- Input
- Audio
- Output
- Text
Playground
Try Gemini 3 Flash by Google Gemini. Requests use the selected workspace’s credits and API pricing.
Providers
Compare available endpoints, pricing, and context limits for Gemini 3 Flash.
| Provider | Context | Output | Input Price | Output Price | Endpoint |
|---|---|---|---|---|---|
| Google Gemini | Not specified | Text | $0.0024 / minute | — | gemini/gemini-3-flash:gemini |
Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max bytes | 20000000 |
| Max seconds | Not specified |
| Formats | aac, flac, mp3, mpeg, mpga, ogg, wav |
Provider Notes
Gemini transcription is prompted multimodal generation rather than a dedicated realtime STT endpoint. The transcribe slug requests a structured transcript; the other model slugs request verbatim text using their exact Gemini model. Inline audio is capped at 20 MB. Gemini 2.5 Pro, Flash, and Flash-Lite return 'no longer available to new users' on generateContent as of July 2026, so their generic STT slugs are intentionally removed; this does not affect the separately named 2.5 TTS or native-audio products. AudioLab does not pass media_resolution for audio because Gemini documents that control for image, video, and PDF media, not audio.
Performance
Status
Current catalog availability. Your workspace’s access is checked separately before a request runs.
A live availability check is not available right now.
Getting Started
Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.
curl "$AUDIOLAB_API_URL/v1/audio/transcriptions" \
-H "Authorization: Bearer $AUDIOLAB_API_KEY" \
-F 'model=gemini/gemini-3-flash' \
-F 'file=@recording.wav'Request Parameters
Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.
| Parameter | Details |
|---|---|
model | gemini/gemini-3-flash — Required model identifier. |
top_p / top_k / candidate_count | View Accepted Values |
max_output_tokens / stop_sequences / seed | View Accepted Values |
thinking_level / include_thoughts | View Accepted Values |
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max bytes | 20000000 |
| Max seconds | Not specified |
| Formats | aac, flac, mp3, mpeg, mpga, ogg, wav |
Similar Models
Explore more speech-to-text and compare their capabilities.
| Model | Context | Input Price | Output Price |
|---|---|---|---|
| Gemini 3.5 TranscribeGoogle Gemini | Not specified | $0.0043 / minute | — |
| Gemini 3.5 FlashGoogle Gemini | Not specified | $0.0024 / minute | — |
| Gemini 3.1 Flash-LiteGoogle Gemini | Not specified | $0.0013 / minute | — |
| Gemini 3.1 ProGoogle Gemini | Not specified | $0.0046 / minute | — |
| Gemini 3.5 Flash TranscribeGoogle Gemini | Not specified | $0.0024 / minute | — |
| MAI-Transcribe 2Microsoft Azure | Not specified | $0.0014 / minute | — |
