Speech and voice providers
Configuring text-to-speech, speech-to-text and talking-avatar providers in Aimogen Pro, including OpenAI, ElevenLabs, Google, Azure Speech and D-ID.
Aimogen Pro uses speech services in three places: reading chatbot replies aloud, generating audio versions of posts, and transcribing uploaded audio. Credentials live in Settings › API Keys; behaviour is configured per feature.
At a glance#
| Provider | Credential | Used for |
|---|---|---|
| OpenAI | main OpenAI key | Text-to-speech and speech-to-text |
| ElevenLabs | ElevenLabs.io API Key | Text-to-speech, voice cloning |
| Google Text-to-Speech | Google Text-to-Speech API Key | Text-to-speech |
| Azure Speech Services | Azure Speech Services API Key | Text-to-speech and talking avatars |
| D-ID | D-ID API Key | Talking avatar video |
OpenAI#
Uses the OpenAI key already configured.
Speech-to-text models: whisper-1, gpt-4o-mini-transcribe, gpt-4o-transcribe. This is the only
transcription backend in the plugin, used by the
audio converter shortcode, the
speech-to-text OmniBlock and the
AI Content Editor audio tools.
Text-to-speech offers a voice selector, an output format and a speed control, configured under AI Chatbot › Text-to-Speech/Video and in the AI Content Editor.
ElevenLabs#
Key: elevenlabs.io → Settings › API Keys › ElevenLabs.io API Key.
The plugin fetches your available voices and caches them in the aiomatic_elevenlabs option, merged with
a built-in default list (Rachel, Domi, Bella, Antoni, Elli, Josh, Arnold, Adam, Sam).
Voice parameters, under AI Chatbot › Text-to-Speech/Video:
| Setting | What it does |
|---|---|
Select a Voice | One of your voices, or a stock voice |
Custom Voice ID | Use a cloned or custom voice by ID instead of the dropdown |
Voice AI Model | Which ElevenLabs model renders the audio |
Voice Stability | Low values give more emotional range and more variance between renders; high values are more consistent and flatter |
Voice Similarity Boost | How closely the output tracks the reference voice. Very high values can amplify artefacts from the source recording |
Style Exaggeration | Amplifies the voice stylistic character. Costs latency |
Speaker Boost | Improves similarity at some processing cost |
ElevenLabs is generally the best-sounding of the four for English narration.
Google Text-to-Speech#
Key: a Google Cloud API key with the Cloud Text-to-Speech API enabled → Settings › API Keys › Google Text-to-Speech API Key.
Voices are fetched and cached in the aiomatic_google_voices option.
| Setting | What it does |
|---|---|
Voice Language | Language and locale, which filters the voice list |
Voice Name | A specific Google voice |
Voice Model | Standard, WaveNet, Neural2 and similar tiers. Higher tiers sound better and cost more |
Audio Device Profile | Optimises the audio for a playback device class, for example headphones or a phone speaker |
Voice Speed | Playback rate |
Voice Pitch | Pitch shift |
Google has by far the widest language coverage of the four.
Azure Speech Services#
Key: an Azure Speech resource key → Settings › API Keys › Azure Speech Services API Key.
Azure powers both plain text-to-speech and the talking avatar feature, where a rendered character speaks the reply on a canvas.
| Setting | What it does |
|---|---|
Azure API Key Region | Must match the region your Speech resource was created in |
Chatbot Avatar Character | Which stock avatar to render |
Chatbot Avatar Character Style | Pose and framing |
Chatbot Avatar Canvas Width | Rendered width in pixels |
Chatbot Voice | The Azure neural voice |
Chatbot Voice Profile ID | Optional custom voice profile |
Private Azure Speech Resource Endpoint URL | Optional private endpoint |
Custom Voice Deployment ID | Optional custom voice deployment |
D-ID#
Key: studio.d-id.com account settings → Settings › API Keys › D-ID API Key.
D-ID animates a still photograph so it appears to speak the reply.
| Setting | What it does |
|---|---|
Actor Source Image URL | A photograph of the face to animate. A clear, front-facing portrait works best |
Select a Voice | The D-ID voice |
AI Talking Avatar Width / Height | Rendered size |
D-ID supports a streaming mode for lower latency. See Voice, speech and talking avatars.
Usage limits#
Speech is metered separately from text. System & Logs › Text-to-Speech Limits provides its own credit pool with the same structure as the text limits: per-user and per-guest credits, a time frame, and an absolute or rolling window.
Configure this before exposing voice output to visitors. Speech is billed per character and adds up much faster than people expect. See Usage limits and credits.
Choosing#
| Goal | Suggestion |
|---|---|
| Best English narration | ElevenLabs |
| Widest language coverage | |
| Enterprise Azure estate, or a rendered avatar | Azure Speech Services |
| Fewest extra accounts | OpenAI |
| A photorealistic talking person | D-ID |
Common problems#
No voices in the dropdown The key is missing or wrong, so the voice list could not be fetched. Re-save the API key.
Azure avatar shows nothing Free tier, wrong region, or an ad blocker. All three are common.
Audio cuts off The text exceeded the provider per-request character limit. Split long content.
Costs higher than expected Speech is per character. Add a text-to-speech limit.
Related#
Still stuck? Open a support ticket and include the diagnostics from Aimogen Pro › System & Logs › System Info.