# Gemini 3.5 Transcribe Live

> Google Gemini 3.5 low-latency speech-to-text over the Live API for bidirectional streaming audio transcription.

Agent resources: the index of everything machine-readable is https://www.ohmygpt.com/llms.txt; the integration skill (endpoints, auth, SDK and coding-tool setup) is https://www.ohmygpt.com/skill.md.

- Model ID: `google/gemini-3.5-transcribe-live`
- Live status and providers as JSON, no key needed: https://api.ohmygpt.com/v1/models/google/gemini-3.5-transcribe-live
- Released: 2026-08-26
- Context: 131K tokens
- Max output: 66K tokens
- Input: audio; output: text

## Prices (USD)

| Item | Price | Unit |
| --- | --- | --- |
| Input | $3.15 | per 1M tokens |
| Output | $18.90 | per 1M tokens |
| Cache read | $3.15 | per 1M tokens |
| Reasoning output | $18.90 | per 1M tokens |
| Audio input | $3.15 | per 1M tokens |

## Providers

Without a prefix each request goes to the best-priced healthy provider. To pin one, send the model as `<provider>:google/gemini-3.5-transcribe-live`.

| Provider | Pinned model ID | Location | Input | Output | Trains on your data |
| --- | --- | --- | --- | --- | --- |
| Google (Gemini) | `google:google/gemini-3.5-transcribe-live` | United States | $3.15 | $18.90 | no |

Web page: https://www.ohmygpt.com/models/google/gemini-3.5-transcribe-live