Built by Metorial, the integration platform for agentic AI.
Provider Summary
convert text to speech
generate audio files
browse available voices
filter voices by language
adjust speech pitch
control speaking rate
adjust audio volume
combine multiple voices
download generated audio
transcribe audio files
download transcripts and subtitles
Generate spoken audio with multiple voices and per-segment speech controls, browse voices by language, and transcribe audio into downloadable transcripts and SRT subtitles.
Use list_voices before generate_audio. Audio generation provides a downloadable file and preserves its original audioBase64 output for existing workflows. The audio format is detected from the returned content; the API does not expose an output-format selector.
For speech recognition, submit Base64-encoded MP3, WAV, FLAC, or OGG audio with create_transcription, then poll get_transcription using the returned job ID. Completed jobs provide transcript and subtitle downloads. Uploaded audio must be no larger than 10 MB.
Connect with an API key from My Profile → API. API access requires an eligible plan and character credit. See the official text-to-speech API and speech-to-text API documentation.
This integration is licensed under the FSL-1.1.
Built with ❤️ by Metorial