Last updated
What is Google Gemini speech-to-text used for in a Bolna voice agent?
Gemini speech-to-text transcribes the caller in real time for your Bolna agent, using Google's gemini-3.5-transcribe-live model over the Gemini Live API. It streams interim words while the caller talks and finalizes each turn at the natural pause, so barge-in stays responsive. It works on 8 kHz phone calls and 16 kHz web calls with no extra setup.
How do I set up Gemini speech-to-text with Bolna?
- Open your agent at platform.bolna.ai and go to the Languages tab.
- Under Transcription, select
Gemini 3.5 Transcribeas the transcriber. - Choose the language your callers speak, for example Hindi or English.
- On the Engine tab, tune Endpointing if needed. Gemini is one of the transcribers that uses this slider.
- To use your own Google account, add your
GOOGLEkey in Settings → Integrations under the STT filter.
In the API, set provider to gemini and model to gemini-3.5-transcribe-live. See the Gemini transcriber guide in the Bolna docs.
Which languages does Gemini speech-to-text support on Bolna?
| Language | Code |
|---|---|
| English, English (India), English (UK) | en, en-IN, en-GB |
| Hindi | hi |
| Tamil, Telugu | ta, te |
| Kannada, Malayalam | kn, ml |
| Marathi, Gujarati, Bengali | mr, gu, bn |
| Spanish, French, German | es, fr, de |
| Italian, Portuguese, Dutch | it, pt, nl |
| Arabic, Indonesian | ar, id |
The model is gemini-3.5-transcribe-live, shown in the dashboard as Gemini 3.5 Transcribe.
What can you build with Gemini and Bolna?
Indian-language agents. Gemini covers Hindi and seven other Indian languages on Bolna. Set the language explicitly and the model keeps handling stray English words without dropping the turn.
One agent for many markets. The same provider covers India, Europe, the Middle East and Indonesia, which keeps configuration simple across regions.
Google-based stacks. Pair it with the Gemini LLM on the same GOOGLE key. If you want one model that hears and speaks, see Gemini Live instead.
Phone and web agents from one config. Gemini handles both 8 kHz telephony and 16 kHz browser audio, so a support agent can serve Plivo calls and web calls the same way.