Mintplex-Labs/anything-llm · error · Error

Deepgram transcription failed (${response.status}) - ${errBo

Error message

Deepgram transcription failed (${response.status}) - ${errBody}

What it means

Thrown when the Deepgram pre-recorded REST API returns a non-OK HTTP status. The response status code and best-effort body text are embedded in the message. This wraps Deepgram-side failures: authentication, bad request, quota, rate limit, or server errors. The error is re-thrown after logging.

Source

Thrown at server/utils/SpeechToText/deepgram/index.js:61

   * @returns {Promise<string>} The transcribed text.
   */
  async transcribe(audioBuffer, filename = "audio.webm") {
    const url = new URL(this.endpoint);
    url.searchParams.set("model", this.model);
    url.searchParams.set("smart_format", "true");

    return await fetch(url.toString(), {
      method: "POST",
      headers: {
        Authorization: `Token ${this.apiKey}`,
        "Content-Type": this.#contentTypeFromFilename(filename),
      },
      body: audioBuffer,
    })
      .then(async (response) => {
        if (!response.ok) {
          const errBody = await response.text().catch(() => "");
          throw new Error(
            `Deepgram transcription failed (${response.status}) - ${errBody}`
          );
        }
        return response.json();
      })
      .then((result) => {
        return (
          result?.results?.channels?.[0]?.alternatives?.[0]?.transcript ?? ""
        );
      })
      .catch((error) => {
        this.#log(`Deepgram transcription failed - ${error.message}`);
        throw new Error(`Deepgram transcription failed - ${error.message}`);
      });
  }
}

module.exports = { DeepgramSTT };

View on GitHub (pinned to 526360e320)

Solutions

1. Match the HTTP status: 401/403 → regenerate STT_DEEPGRAM_API_KEY; 400 → check STT_DEEPGRAM_MODEL and audio format; 402 → check billing; 429 → back off; 5xx → retry shortly.
2. Read errBody in the message — Deepgram returns a JSON reason string that pinpoints the problem.
3. Confirm STT_DEEPGRAM_MODEL is a valid model id for your Deepgram account tier.
4. Ensure the audio buffer is non-empty and a supported codec; convert to WAV via the helpers if unsure.
5. Check Deepgram status page for ongoing incidents.

// Pre-flight the key/model cheaply is not possible; validate config shape instead.
if (!process.env.STT_DEEPGRAM_API_KEY) {
  throw new Error("STT_DEEPGRAM_API_KEY is required for Deepgram STT.");
}

async function transcribeWithRetry(stt, buf, name, attempts = 2) {
  for (let i = 0; i < attempts; i++) {
    try {
      return await stt.transcribe(buf, name);
    } catch (e) {
      const m = e.message || "";
      const retriable = /\(429\)|\(5\d{2}\)/.test(m);
      if (!retriable || i === attempts - 1) throw e;
      await new Promise((r) => setTimeout(r, 500 * Math.pow(2, i)));
    }
  }
}

When it happens

Trigger: 401/403 from an invalid or expired STT_DEEPGRAM_API_KEY; 400 from an invalid STT_DEEPGRAM_MODEL (e.g. a typo) or an audio container Deepgram cannot parse; 402 account out of credits; 429 rate limit; 5xx Deepgram outage.

Common situations: Wrong/revoked API key; mistyped model name (nova-3 vs nova-2); sending an audio format not in the Content-Type map (defaults to audio/webm); burst of requests hitting rate limits; Deepgram incident.

Related errors

• Deepgram transcription failed - ${error.message}
• HTTP ${res.status}: ${res.statusText}
• res.statusText || "Error generating api key."
• res.statusText || "Error finding custom models."
• AnthropicLLM::getChatCompletion failed to communicate with A

AI-assisted analysis of Mintplex-Labs/anything-llm@526360e320 (2026-08-13). Data as JSON: /api/errors/f85aeaee4c1acc5d. Report an issue: GitHub.