Typecast and Salesflare
How to connect Typecast
- Via Zapier — 9 operations available. Set it up ↗
- Via Make — 7 modules available. Set it up ↗
About Typecast
Typecast is an AI text-to-speech API that converts text into lifelike, expressive speech in many languages.
Typecast operations on Zapier
Actions (5)
Things Salesflare can make it do
- Clone Voice — Creates a quick-cloned custom Typecast voice from a WAV or MP3 audio sample.
- Create Speech From Text — Converts text to speech using Typecast AI voice models. Supports ssfm-v30 and ssfm-v31 with context-aware emotion inference.
- Create Speech With Timestamps — Converts text to speech and returns word- or character-level alignment alongside the audio. Useful for generating subtitles, karaoke captions, or syncing visuals to narration.
- Create Streaming Speech From Text — Converts text to speech using Typecast streaming TTS and returns the streamed audio as a Zapier file URL.
- Delete Cloned Voice — Deletes a quick-cloned custom Typecast voice by its uc_ voice ID.
Searches (4)
Look up existing records
- Get My Subscription — Returns the authenticated user plan tier, credit usage, and concurrency limit. Useful for quota-aware batching, plan gating, and rate-limit guards in your Zaps.
- Get Voice by ID — Get detailed information for a specific voice with enhanced metadata.
- List Voices — Lists all available voice models with enhanced metadata. Filter by model, gender, age, or use case.
- Recommend Voices — Recommends voices from a text description. Results contain only voice IDs, names, and scores; use Get Voice by ID or List Voices for detailed metadata.
Typecast operations on Make
Actions (4)
Things Salesflare can make it do
- Clone a Voice — Creates a quick-cloned custom voice from an incoming WAV or MP3 audio file. The returned voice ID can be used in Generate a Speech.
- Delete a Cloned Voice — Deletes a quick-cloned custom voice by its uc_ voice ID.
- Generate Speech with Timestamps — Generates speech for a given text and returns word- or character-level timestamp alignment alongside the audio. Useful for generating subtitles, karaoke captions, or syncing visuals to narration. Languages without word boundaries (Japanese, Chinese) should pick Character or Both for the Granularity option.
- Generate a Speech — Generates speech for a given text.
Searches (3)
Look up existing records
- Get My Subscription — Returns the authenticated user plan tier, credit usage, concurrency limit, and custom voice slot count. Useful for quota-aware batching, plan gating, and rate-limit guards inside scenarios.
- Get Voice — Retrieves voice details for the given voice id.
- Get Voices — Listing all voices that TTS model supports.
Similar apps
OpusClip is a AI video tool that turns long videos into viral shorts with captions and transcrip…
ElevenLabs is an AI audio research and deployment company.
Meet HeyGen - The best AI video generation platform for your team.
Gamma is an AI-powered design partner that helps create professional-looking presentations, docu…
Create and ship an entire marketing campaign in 60 seconds.
Video drives action. Now you can automatically enrich all your transactional emails with persona…
Not using Salesflare yet?
Salesflare is a CRM for small and medium-sized B2B businesses — it fills itself in automatically so your team actually keeps it up to date.
Try it for free