feat(media-understanding): add Telnyx STT provider

Add native Telnyx Speech-to-Text support using the OpenAI-compatible
REST API at https://api.telnyx.com/v2/ai/audio/transcriptions.

- Add telnyxProvider with audio transcription capability
- Reuse transcribeOpenAiCompatibleAudio since Telnyx follows OpenAI format
- Add default model: openai/whisper-large-v3-turbo
- Add tests for the new provider

Co-Authored-By: Claude (anthropic/claude-opus-4-5) <noreply@anthropic.com>

2026-01-30 11:36:06 -03:00

1.9 KiB

Raw Blame History

summary

read_when

Telnyx speech-to-text for inbound voice notes

You want Telnyx speech-to-text for audio attachments

You need a quick Telnyx STT config example

Telnyx (Audio Transcription)

Telnyx provides speech-to-text via their AI API powered by Whisper. In Moltbot it is used for inbound audio/voice note transcription via tools.media.audio.

When enabled, Moltbot uploads the audio file to Telnyx and injects the transcript into the reply pipeline ({{Transcript}} + [Audio] block). This is not streaming; it uses the pre-recorded transcription endpoint.

Website: https://telnyx.com Docs: https://developers.telnyx.com/docs/voice/programmable-voice/stt-standalone

Quick start

Set your API key:

TELNYX_API_KEY=KEY...

Enable the provider:

{
  tools: {
    media: {
      audio: {
        enabled: true,
        models: [{ provider: "telnyx", model: "openai/whisper-large-v3-turbo" }]
      }
    }
  }
}

Options

model: Telnyx model id (default: openai/whisper-large-v3-turbo)
language: language hint (optional)

Example with language:

{
  tools: {
    media: {
      audio: {
        enabled: true,
        models: [
          { provider: "telnyx", model: "openai/whisper-large-v3-turbo", language: "en" }
        ]
      }
    }
  }
}

Available models

Telnyx offers Whisper-based transcription models:

openai/whisper-large-v3-turbo (default) - Fast, high-quality transcription
openai/whisper-large-v3 - Higher accuracy, slightly slower

Notes

Authentication follows the standard provider auth order; TELNYX_API_KEY is the simplest path.
The API follows OpenAI's transcription format, making it compatible with existing tooling.
Override endpoints or headers with tools.media.audio.baseUrl and tools.media.audio.headers when using a proxy.
Output follows the same audio rules as other providers (size caps, timeouts, transcript injection).

1.9 KiB Raw Blame History