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
- Settings → Voice & Speech → Speech-to-text Preference, provider Any OpenAI Compatible STT Service (Generic OpenAI).
- Fill in:
| Base URL | https://glyphcall.com/v1 |
|---|---|
| API Key | adt_… (your key) |
| Transcription Model | whisper-1 |
3. Audio and video files in your workspaces
- Settings → Transcription, provider OpenAI Compatible.
- 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
- Settings → Voice & Speech → Text-to-speech Preference, provider OpenAI Compatible.
- Fill in:
| Base URL | https://glyphcall.com/v1 |
|---|---|
| API Key | adt_… (your key) |
| TTS Model | tts-1 |
| Voice Model | nova |
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
| Call | Price |
|---|---|
| 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