Connect Voicemaker to Your AI Agent

Find a voice for the narration language, then provide the final script and voice ID for synthesis.

2 tools API key

Connect Voicemaker Install OOMOL

Try a Voicemaker Task

Copy a prompt into your agent with the oo Skill installed. Add your page links and source notes before running it.

oo Skill Voicemaker

Choose a Narration Voice

Find a supported voice for your narration language.

/oo Voicemaker: List voices for language [language] and summarize the available voice options.

Generate Narration Audio

Synthesize the supplied script with a chosen voice and return its audio link.

/oo Voicemaker: Synthesize text [Text] with voice [VoiceId] and return the audio URL.

Start Working with Voicemaker

Install OOMOL

Set up oo CLI and the oo Skill in your agent.
Install OOMOL →
Connect Voicemaker

Connect with your Voicemaker API Key.
Connect Voicemaker →
Give Your Agent a Task

Use /oo with the pages to read, the changes to make, and where to save the result.
Connection Guide →

Choose Your Agent

Codex Claude Code Cursor Hermes

Synthesis quota and a voice ID selected from the available voices.
Speech generation returns an audio URL and usage details; it does not transcribe audio.

Voicemaker Tools

Voicemaker converts text or SSML to speech. The integration lists available voices and returns generated audio links with usage details from synthesis requests.

Choose a Narration Voice

List Voicemaker text-to-speech voices, optionally filtered by language.

Generate Narration Audio

Convert text to speech and return the generated audio URL and usage details.

2 tools

List Voices

List Voicemaker text-to-speech voices, optionally filtered by language.

voicemaker.list_voices

Generate Tts

Convert text to speech and return the generated audio URL and usage details.

voicemaker.generate_tts

Frequently Asked Questions

What can AI help me do with Voicemaker?

Ask for voices in a chosen language or generate narration from supplied text using a specific VoiceId. The result is synthesized speech rather than audio transcription.

What should I know before using Voicemaker results?

Speech generation returns an audio URL and usage details; it does not transcribe audio.

What do I need to connect Voicemaker?

Use a Voicemaker developer API key with synthesis quota. Select a voice ID from the available voices before generating audio.