Glyphcall Voice in the apps you already use
These apps let you choose the speech service. Paste one URL and one key and they get natural voices and Whisper transcription, paid per call.
- Open WebUI voice without a GPU: hosted text to speech and Whisper
Set Open WebUI's Audio settings to a hosted OpenAI-compatible endpoint: natural voices for read-aloud and Whisper for voice input, pay per call, no OpenAI account. - LibreChat voice: hosted Whisper and text to speech in librechat.yaml
librechat.yaml speech settings for a hosted OpenAI-compatible endpoint: Whisper speech to text and natural text to speech, pay per call. - AnythingLLM: hosted Whisper transcription and text to speech
Set AnythingLLM's OpenAI-compatible speech-to-text, transcription and text-to-speech providers to a hosted endpoint, pay per call. - Home Assistant text to speech: the OpenAI TTS integration with a custom endpoint
Use the HACS OpenAI TTS integration (sfortis/openai_tts) with a hosted OpenAI-compatible endpoint: natural voices for announcements, pay per call. - Obsidian Whisper plugin with a different API URL
Set the Obsidian Whisper plugin's API URL to a hosted Whisper-compatible endpoint: voice notes to text at one cent per recording, no OpenAI account. - A hosted OpenAI-compatible speech endpoint for any app
Base URL, key and model names for apps with an OpenAI-compatible text-to-speech or speech-to-text setting: SillyTavern, VoiceInk, dictation apps, browser readers and your own code. - OpenAI is shutting down tts-1: what breaks and how to move
OpenAI retires tts-1, tts-1-hd and gpt-4o-mini-tts on 6 January 2027. What stops working, how to keep the same /v1/audio/speech request with another base URL. - OpenAI is shutting down whisper-1: what breaks and how to move
OpenAI retires whisper-1 and the gpt-4o transcribe models on 26 February 2027. What stops working, how to keep the same /v1/audio/transcriptions request with another base URL.
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.