Skip to content
Soniox

Soniox speech-to-text for Bolna AI voice agents

Soniox is a real-time speech-to-text provider that transcribes your callers with a single multilingual model, stt-rt-v5, which switches languages mid-sentence over one streaming connection. Pick it when callers mix English with a regional language, such as Hinglish, and you don't want to fix a language per call.

How Soniox fits in the stack.

  • Best for

    Turning the caller's speech into text in real time, in their language.

  • Use this layer when

    You want to tune accuracy, latency, languages or vocabulary for your callers.

  • Connects to

    The phone call upstream, and the LLM that reads the text downstream.

The transcriber is the
listening layer.

Soniox turns the caller's speech into text as they talk, so the LLM can understand it and reply.

  1. Telephony

    Phone network

    • Exotel
    • Plivo
    • Twilio
  2. STT · You are here

    Listener

    • Soniox
  3. LLM

    Reasoning

    • OpenAI
    • Anthropic
    • Google Gemini
  4. TTS

    Voice

    • ElevenLabs
    • Sarvam AI (TTS)
    • Cartesia
  5. Tools

    Actions

    • Cal.com
    • n8n
    • AiSensy

How do I set up Soniox with Bolna?

Which Soniox models and languages does Bolna support?

ModelLanguages on BolnaFeatures
stt-rt-v5 (Soniox v5)Multilingual auto-detect, English (en), English India (en-IN), Hindi (hi), Bengali (bn), Tamil (ta), Telugu (te), Gujarati (gu), Kannada (kn), Malayalam (ml), Marathi (mr), Punjabi (pa)Code-switching, per-token language identification, semantic endpoint detection, keyword and context biasing, 8 kHz telephony and 16 kHz web calls

For language codes and biasing, see the Soniox setup guide in the Bolna docs.

For Indian-language-only agents, the docs suggest comparing Soniox with Sarvam speech-to-text.

What can you build with Soniox and Bolna?

  • Hinglish sales and collections

    Handle callers who mix English and Hindi on outbound calls without reconfiguring the transcriber per contact.

  • One agent for many languages

    Serve callers across the supported languages from a single agent instead of a separate agent or IVR branch per language.

  • Faster turn-taking

    Semantic endpoint detection spots when the caller has actually finished, so the agent replies sooner without cutting people off.

  • A single Soniox key for voice and transcription

    Pair the transcriber with Soniox text-to-speech, since one SONIOX key serves both.

Other providers in this layer.

See all 10 speech-to-text providers
  • AssemblyAI

    Speech-to-text

    AssemblyAI Universal-3.6 Pro transcribes callers for your Bolna voice agent in 32 languages, with code-switching and keyword plus context biasing.

  • Azure Speech-to-Text

    Speech-to-text

    Azure Speech-to-Text transcribes callers in real time for a Bolna voice agent, with speaker diarization, language identification and phrase lists of up to 2,000 terms.

  • Deepgram

    Speech-to-text

    Deepgram is Bolna's default English transcriber, turning caller speech into text with Nova-3, Nova-2 or Flux streaming models on live phone calls.

Keep exploring the voice stack.

See where Soniox fits in your workflow.

Walk through provider choice, stack trade-offs and the exact workflow you want Bolna to automate.

Ready for enterprise.

Secure, compliant and dependable, from the first pilot to full scale.

Contact Sales
  • 99.9% uptime

    Built for your busiest hour. Even if the model fails, the call doesn’t

  • Support and SLAs

    A dedicated team, with service levels shaped around your business

  • Security & compliance

    Data residency, encryption, access controls, full audit trails and more

  • Deploy in your cloud

    Run Bolna in your own cloud or on-premise, your data remains yours

Certified by

  • ISO 27001
  • DPDP compliant

Frequently Asked Questions

Yes. Select the multilingual option and Soniox detects and code-switches between English and Hindi in one stream, without you setting a language up front.