Glyphcall Voice

AnythingLLM: hosted Whisper transcription and text to speech

AnythingLLM has an OpenAI-compatible provider for voice input, for transcribing audio files and for read-aloud. The same base URL and key go into all three.

1. Get a key

Get an access key on the pricing page: $1 once (1,000 credits) or $3 a month (3,000 credits, about 60 hours). After paying you get a page that shows the key (it starts with adt_). That key is the API key in every app below.

2. Voice input

  1. Settings → Voice & Speech → Speech-to-text Preference, provider Any OpenAI Compatible STT Service (Generic OpenAI).
  2. Fill in:
Base URLhttps://glyphcall.com/v1
API Keyadt_… (your key)
Transcription Modelwhisper-1

3. Audio and video files in your workspaces

  1. Settings → Transcription, provider OpenAI Compatible.
  2. Use the same three values as above.

Files up to 5 MB cost $0.01 each; larger MP3 or WAV files up to 60 minutes cost $0.05.

4. Read-aloud

  1. Settings → Voice & Speech → Text-to-speech Preference, provider OpenAI Compatible.
  2. Fill in:
Base URLhttps://glyphcall.com/v1
API Keyadt_… (your key)
TTS Modeltts-1
Voice Modelnova

Docker or server .env

TTS_PROVIDER="generic-openai"
TTS_OPEN_AI_COMPATIBLE_ENDPOINT="https://glyphcall.com/v1"
TTS_OPEN_AI_COMPATIBLE_KEY="adt_your_key"
TTS_OPEN_AI_COMPATIBLE_MODEL="tts-1"
TTS_OPEN_AI_COMPATIBLE_VOICE_MODEL="nova"

Test the key first

If something does not work in the app, check the key and the endpoint with one call from a terminal:

curl https://glyphcall.com/v1/audio/speech \
  -H "Authorization: Bearer YOUR_KEY" -H "Content-Type: application/json" \
  -d '{"model":"tts-1","input":"Hello from Glyphcall Voice.","voice":"nova"}' -o hello.mp3

What it costs

CallPrice
Text to speech, up to 300 characters$0.01 (10 credits)
Text to speech, 301 to 2,000 characters$0.08 (80 credits)
Speech to text, a file up to 5 MB$0.01 (10 credits)
Speech to text, a larger MP3 or WAV up to 60 minutes / 25 MB$0.05 (50 credits)

A failed call is never charged. No account, no subscription unless you choose the monthly plan.

Questions

Why does the Base URL end in /v1? AnythingLLM adds /audio/transcriptions or /audio/speech itself.

Is my audio stored? No. The file is used for that one request and not kept.

Other guides: Open WebUI · LibreChat · Home Assistant · Obsidian Whisper · Any other app · OpenAI tts-1 shutdown · OpenAI whisper-1 shutdown · Voice list