Skip to main content
An Odia voice agent on Bolna is a regular agent whose transcriber (speech-to-text) and voice (text-to-speech) are both set to Odia, with a prompt written in Odia script. This page lists the providers whose Bolna docs confirm Odia support, the language code to send, and a minimal API example. Bolna’s language code for Odia is od, except on Maya, which takes or. Odia is not one of the languages Bolna detects automatically mid-call. If you want one agent that handles both English and Odia on the same call, start here for the Odia side, then follow Set up multilingual voice AI agents. For every language, see the languages overview.

Choose an Odia transcriber

The transcriber turns the caller’s Odia speech into text. Send the plain code od as transcriber.language, not a locale such as od-IN (Create Agent). For callers in India, the Sarvam page calls Sarvam usually the strongest transcriber choice. Compare all transcribers in Choosing a speech-to-text provider.

Choose an Odia voice

The voice (synthesizer) speaks the agent’s replies. Set language inside provider_config to od on Sarvam and or on Maya (Create Agent). Voice catalogs change over time. Confirm a valid model and voice_id pair with List voices, or preview voices in the Languages tab. See Choosing a text-to-speech provider for a wider comparison.

Write the prompt for Odia

  • Write in Odia script, not romanized Odia. ନମସ୍କାର! ଆପଣ କେମିତି ଅଛନ୍ତି? rather than Namaskar! Apana kemiti achhanti?. Native script gives more accurate pronunciation and stops the text being treated as English.
  • Keep common English loanwords in Latin script. Callers say “order”, “OTP” and “support ticket” in English, so keep those words as they are inside Odia script text instead of forcing a pure Odia translation.
  • Set gender and politeness explicitly. These are often carried by verb forms, so name the forms you want for the agent’s persona rather than writing “be polite”.
  • Read alphanumerics character by character, in English. For OTPs, registration numbers and order IDs, this avoids misheard and mispronounced digits.
  • Leave language switching out of the prompt. Bolna switches languages itself.
The full guidance, with examples, is in Writing prompts in non-English languages.

Create an Odia agent over the API

This uses the same body shape as the API quickstart, with Sarvam for both transcription and voice.
1

Write the agent config

Save this as agent.json:
The voice is priya, one of the 16 bulbul:v3 voices that work in every Bulbul language. sampling_rate and encoding are left out because Bolna sets them for Sarvam to match the telephony provider.
2

Create the agent

The response contains the new agent_id.
3

Place a test call

Call the agent with POST /call, as in the API quickstart, and check the transcript with GET /executions/{id}.
To use another provider, swap the transcriber or synthesizer block for one from the provider’s page. Every combination is validated when you create the agent: an unsupported transcriber model and language pair returns 400 Provided language: <language> is not available for the model: <model>.

Improve recognition with keywords and context

Brand names, product names and place names are where Odia transcription most often goes wrong. Bolna has two transcriber fields for this:
  • keywords: a comma-separated list of terms callers say.
  • context: a sentence or two describing the call.
Support for Odia transcribers:
  • Sarvam: keywords on Sarvam needs saaras:v4, and takes up to 50 terms of up to 64 characters each. context works on every Saaras model.
Sarvam transcribes English words in the native script of the call’s language. On an Odia agent, a boosted term such as PhonePe can come back in Odia script rather than Latin script.
See Keywords and context for the full provider support table and how to write good terms.

Serve Odia and English on one agent

Many callers move between Odia and English. Bolna handles this in two ways:
  • Code-mixing within a sentence. Sarvam handles switching between English and an Indian language inside a single sentence. A sentence with a few English words is still treated as Odia.
  • A full language switch. Add both English and Odia to one agent with multilingual_config, each with its own transcriber, voice and prompt. Odia is not in the automatic detection list, so don’t rely on a mid-call switch into Odia. Start Odia callers in Odia instead, as below. The multilingual quickstart shows the API shape.
On a multilingual agent, you can also:
  • Start a call in Odia with "agent_data": { "language": "od" } on POST /call, or an agent_language column set to od in a batch CSV. Inbound calls can return agent_language from your caller data source.
  • Let system messages such as the hangup and “are you still there?” checks follow the active language.
  • Read How language switching works for what does and doesn’t trigger a switch.

Notes

  • Bolna’s code for Odia is od, on the transcriber, on Sarvam’s voice and in multilingual_config. Maya is the exception: its provider_config.language takes or.
  • On Sarvam, use bulbul:v3 for Odia. bulbul:v4-flash has no Odia voices.
  • Odia is not one of the languages Bolna detects automatically mid-call. Start Odia callers in Odia, or make Odia the agent’s default language.
  • Sarvam is the only transcriber whose page lists Odia. The Cartesia page notes that Odia is not yet selectable in Bolna on sonic-3.6.

Phone numbers for Odia agents in India


Next steps

Languages overview

Every language with a guide, and its providers

Multilingual setup

Indian language support by provider, and per-language voices and prompts

Sarvam speech-to-text

Saaras models, language codes and biasing limits

Sarvam text-to-speech

Bulbul models and voice catalogs per language

Start a call in a language

Pick the opening language per call, batch row or inbound caller

How language switching works

What does and doesn’t trigger a mid-call switch