Transcriber
Google Gemini (STT) logo

Google Gemini speech-to-text for Bolna AI voice agents

Google's Gemini 3.5 Transcribe gives a Bolna voice agent streaming speech-to-text in 19 language codes, including Hindi, Tamil and Bengali, on phone and web calls.

stttranscribergeminigooglespeech-to-textmultilingual
At a glance

How Google Gemini (STT) fits in the stack

Best for

Turning noisy phone audio into text the agent can reason over.

Use this layer when

Recognition accuracy, language coverage, and latency matter most.

Connects to

Telephony audio upstream and your LLM downstream.

Voice Stack

Speech-to-text is the listening layer

Speech-to-text is the listening layer

This provider converts raw audio into text in real time. It shapes how accurately the agent hears the caller and how natural the back-and-forth feels.

TelephonyPhone Network
→
STTListener
→
LLMReasoning
→
TTSVoice
→
ToolsActions

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?

  1. Open your agent at platform.bolna.ai and go to the Languages tab.
  2. Under Transcription, select Gemini 3.5 Transcribe as the transcriber.
  3. Choose the language your callers speak, for example Hindi or English.
  4. On the Engine tab, tune Endpointing if needed. Gemini is one of the transcribers that uses this slider.
  5. To use your own Google account, add your GOOGLE key 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?

LanguageCode
English, English (India), English (UK)en, en-IN, en-GB
Hindihi
Tamil, Teluguta, te
Kannada, Malayalamkn, ml
Marathi, Gujarati, Bengalimr, gu, bn
Spanish, French, Germanes, fr, de
Italian, Portuguese, Dutchit, pt, nl
Arabic, Indonesianar, 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.

FAQ

Google Gemini (STT) on Bolna: frequently asked questions

Yes. Select Gemini 3.5 Transcribe on the agent's Languages tab, or set `provider` to `gemini` and `model` to `gemini-3.5-transcribe-live` in the API.

Yes. Bolna supports Hindi, Tamil, Telugu, Kannada, Malayalam, Marathi, Gujarati, Bengali and English (India) on Gemini, along with English, European languages, Arabic and Indonesian.

Yes. Add your `GOOGLE` key in Settings, then Integrations, under the STT filter.

Set it to the language your callers speak. Bolna hints that language to Gemini for the whole call, and the model still handles the occasional word from another language.

Browse this layer

Keep exploring the voice stack

Browse

Speech-to-Text

Speech-to-text converts what callers say into text that your LLM can process. Transcription accuracy and latency directly affect how natural a conversation feels. Bolna supports streaming STT providers optimized for telephony audio, including specialized models for Indian languages.

Browse

Telephony

Telephony providers connect your voice agents to the phone network so they can make and receive real calls. Bolna supports managed integrations with major carriers as well as bring-your-own-carrier via SIP trunking, giving you full control over call routing, number provisioning, and cost.

Browse

Large Language Models

The LLM is the brain of your voice agent. It understands what callers say and decides how to respond. Bolna lets you switch between models like GPT-5.4 mini, Claude and DeepSeek by changing the provider and model in your agent LLM settings, so you can tune for speed, cost or reasoning depth.

Browse

Text-to-Speech

Text-to-speech turns your agent responses into spoken audio. Voice quality shapes how callers perceive your brand. Flat, robotic speech kills trust while natural, expressive voices build it. Bolna integrates with the fastest TTS providers so responses sound human and arrive without awkward pauses.

Browse

Tools & Workflows

Tools let your voice agents take action during a call, not just talk. Book a calendar slot, look up an order through your own API, push a lead into your CRM, or trigger a multi-step automation in Zapier. These integrations turn voice agents from answering machines into workflow engines.

See where Google Gemini (STT) fits in your production workflow

Use the demo to walk through provider selection, stack tradeoffs, and the exact workflow you want Bolna to automate.