> ## Documentation Index
> Fetch the complete documentation index at: https://www.bolna.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Speech-to-text providers

> See every speech-to-text provider you can use as a Bolna agent transcriber, and open the setup guide for each.

The transcriber turns the caller's audio into text in real time. Pick one per language on the agent's **Languages** tab, or set it in the `transcriber` block of the agent config. Each provider below has its own guide with models, configuration and troubleshooting.

Not sure which to choose? [Choose providers](/docs/concepts/choosing-providers) compares them by language, latency and cost. To use your own account with a provider, see [Connect provider credentials](/docs/providers).

<CardGroup cols={2}>
  <Card title="Deepgram" href="/docs/deepgram-transcriber">
    Configure Deepgram Nova-3 or Nova-2 streaming speech-to-text in your Bolna voice agent. Covers models, endpointing, multilingual config, and troubleshooting.
  </Card>

  <Card title="Deepgram Flux" href="/docs/deepgram-flux">
    Use Deepgram's next-generation Flux models with Bolna Voice AI agents for ultra-low-latency streaming transcription and intelligent turn detection.
  </Card>

  <Card title="OpenAI" href="/docs/openai-transcriber">
    Integrate OpenAI's Realtime transcription API with Bolna Voice AI agents for low-latency, streaming speech recognition using GPT Realtime Whisper.
  </Card>

  <Card title="Azure" href="/docs/azure-transcriber">
    Integrate Azure Speech-to-Text with Bolna Voice AI for real-time, multilingual, high-accuracy transcriptions and enterprise-grade scalability.
  </Card>

  <Card title="AssemblyAI" href="/docs/assemblyai">
    Configure AssemblyAI Universal-3.6 Pro streaming speech-to-text in Bolna: models, the 32 supported languages, keyword and context biasing, and troubleshooting.
  </Card>

  <Card title="ElevenLabs" href="/docs/elevenlabs-transcriber">
    Integrate ElevenLabs Scribe with Bolna Voice AI agents for real-time, low-latency speech transcription. Supports word-level timestamps & VAD-based endpointing.
  </Card>

  <Card title="Gladia" href="/docs/gladia">
    Integrate Gladia with Bolna Voice AI agents for real-time multilingual transcription. Supports code-switching, custom vocabulary, and sub-300ms latency.
  </Card>

  <Card title="Sarvam" href="/docs/sarvam-transcriber">
    Integrate Sarvam with your Bolna Voice AI agents for accurate Indian language transcription using Sarvam's Saaras speech recognition models.
  </Card>

  <Card title="Smallest" href="/docs/smallest-transcriber">
    Integrate Smallest AI's Pulse model with Bolna Voice AI agents for ultra-low-latency, high-accuracy speech-to-text transcription.
  </Card>

  <Card title="Soniox" href="/docs/soniox">
    Integrate Soniox real-time STT with your Bolna Voice AI agents for multilingual transcription with native code-switching and low-latency turn detection.
  </Card>

  <Card title="Gemini" href="/docs/gemini-transcriber">
    Integrate Google's Gemini 3.5 Transcribe real-time speech-to-text with your Bolna Voice AI agents for accurate, low-latency transcription across many languages.
  </Card>
</CardGroup>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.