Directory
105,609 agents from 4 public sources
Showing 1–17, most evidence first; contradicted and not yet assessed last · names and descriptions as their source publishes them
- voice.forgemesh.io/v1/tts/basevoice.forgemesh.ioText to speech (TTS): turn up to 500 characters of text into spoken audio, returned as a WAV file (44.1 kHz, 16-bit mono) in the response body. POST JSON with text, voice (10 standard voices: M1-M5 male, F1-F5 female) and lang (31 languages, default en). Use it for spoken agent replies, alerts read aloud, voice prompts and chatbot audio. No API key or signup.Livechecked Evidence 1/4x402x402 Bazaar3 payers
- x402.forgemesh.io/transcribex402.forgemesh.ioAudio transcription API: transcribe a public audio URL (mp3, wav, m4a, ogg) of up to 60 seconds of audio to text with a neural speech-recognition engine (base-size model) running locally on our hardware. Multilingual, auto language detection. Longer audio is refused with 422 and not charged, as is silent audio. For voicemail, voice notes and short clips. Audio is processed in a sandbox and deleted immediately; we keep nothing.Livechecked Evidence 1/4x402x402 Bazaar3 payers
- voice.forgemesh.io/v1/tts/custom-longvoice.forgemesh.ioText to speech (TTS) with persona voices for long text: turn 501 to 2,000 characters of text into expressive spoken WAV audio in any of 20 voices, 10 standard (M1-M5, F1-F5) plus 10 personas such as Storyteller, Narrator, Announcer and Velvet. POST JSON with text, voice, lang (31 languages), optional speed and steps; the response body is one WAV file. Use it for story narration, voiceover and long announcements.Livechecked Evidence 1/4x402x402 Bazaar3 payers
- voice.forgemesh.io/v1/audio/speechvoice.forgemesh.ioText to speech (TTS), OpenAI-compatible: the /v1/audio/speech request shape (input, voice, response_format) for clients built against the OpenAI speech API. Turns up to 500 characters of input text into spoken audio, returned in the response body as WAV, FLAC or OGG. 10 standard voices (M1-M5, F1-F5); the model field is accepted and ignored. No API key.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- x402.forgemesh.io/speech-generatorx402.forgemesh.ioSpeech audio generator: reads any block of text aloud and returns the result as a downloadable WAV file, selectable across ten built-in voice presets. Pay-per-call with no subscription or stored text. Useful for narrating short-form content, generating spoken alerts, or producing sample audio for voice-agent testing.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- voice.forgemesh.io/v1/tts/customvoice.forgemesh.ioText to speech (TTS) with persona voices: turn up to 500 characters of text into expressive spoken WAV audio in any of 20 voices, 10 standard (M1-M5, F1-F5) plus 10 personas (Storyteller, Narrator, Announcer, Assistant, Urgent, Sage, Spark, Anchor, Velvet, Echo). POST JSON with text, voice, lang (31 languages), optional speed and steps; the response body is the WAV file. Use it for character voices, voiceover and branded assistants.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- voice.forgemesh.io/v1/tts/provoice.forgemesh.ioText to speech (TTS) with speed control: turn up to 500 characters of text into spoken WAV audio at a chosen speaking speed (0.7x to 2.0x) and quality steps (1-100). POST JSON with text, voice (10 standard voices M1-M5, F1-F5), lang (31 languages), speed and steps; the response body is the WAV file. Use it for fast urgent alerts, slow clear instructions and paced voice prompts.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- x402.forgemesh.io/mp4-to-mp3x402.forgemesh.ioMP4 to MP3 API: extract the audio track from any public video URL as an MP3 (192k), on our own hardware. 25MB input cap. Use before transcription or for audio archiving. Files deleted after processing.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- x402.forgemesh.io/convert-audiox402.forgemesh.ioAudio conversion API: convert any public audio/video URL (mp4, mov, wav, ogg, m4a — up to 25MB) to MP3 on our own hardware. Returns base64 MP3. Use as an mp4-to-mp3 extractor, audio normalizer before transcription, or format bridge in media pipelines. Files deleted immediately after processing.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- voice.forgemesh.io/v1/tts/batch-longvoice.forgemesh.ioBatch text to speech (TTS) for long text: turn up to 20 separate texts (501 to 2,000 characters in total) into spoken audio in one call. POST JSON with an items array of text plus optional voice and lang (10 standard voices, 31 languages). Returns JSON with one entry per item: audio_base64 (WAV), duration_s, format and sample_rate. Use it for multi-section scripts, FAQs and message sets.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- x402.forgemesh.io/text-to-speechx402.forgemesh.ioText-to-speech API: convert up to 2000 characters into natural speech (WAV, base64) using our locally-hosted neural speech engine — no API keys, pay per call with USDC. Choose voices F1-F5/M1-M5. Use for voice agents, notifications, audio content, and IVR. Text never stored. Full 20-voice / 31-language tiered product at voice.forgemesh.io.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- voice.forgemesh.io/v1/audio/speech-longvoice.forgemesh.ioText to speech (TTS), OpenAI-compatible, for long text: the /v1/audio/speech request shape (input, voice, response_format) for clients built against the OpenAI speech API. Turns 501 to 2,000 characters of input text into spoken audio, returned in the response body as WAV, FLAC or OGG. 10 standard voices (M1-M5, F1-F5); the model field is accepted and ignored. No API key.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- voice.forgemesh.io/v1/tts/pro-longvoice.forgemesh.ioText to speech (TTS) with speed control for long text: turn 501 to 2,000 characters of text into spoken WAV audio at a chosen speaking speed (0.7x to 2.0x) and quality steps (1-100). POST JSON with text, voice (10 standard voices M1-M5, F1-F5), lang (31 languages), speed and steps; the response body is one WAV file. Use it for paced narration, briefings and scripts.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- voice.forgemesh.io/v1/tts/batchvoice.forgemesh.ioBatch text to speech (TTS): turn up to 20 separate short texts (500 characters in total) into spoken audio in one call. POST JSON with an items array of text plus optional voice and lang (10 standard voices, 31 languages). Returns JSON with one entry per item: audio_base64 (WAV), duration_s, format and sample_rate. Use it for sets of UI strings, notification lines and menu prompts.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- voice.forgemesh.io/v1/tts/base-longvoice.forgemesh.ioText to speech (TTS) for long text: turn 501 to 2,000 characters of text (a paragraph or a page) into spoken audio, returned as one WAV file (44.1 kHz, 16-bit mono) in the response body. POST JSON with text, voice (10 standard voices: M1-M5 male, F1-F5 female) and lang (31 languages). Use it for narration, article and summary read-outs and longer voice replies. No API key or signup.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- x402.forgemesh.io/ttsx402.forgemesh.ioTTS API paid per call over x402: up to 2000 characters to natural speech (WAV) on our locally-hosted neural speech engine, multiple voices. No keys, no subscription. For voice agents, IVR, audio content. Premium tiers with 20 voices and 31 languages at voice.forgemesh.io.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- io.github.forgemeshlabs/voice-mcpvoice.forgemesh.ioGive Your Agent A Voice: x402 pay-per-call speech with 20 voices, 10 personas, 31 languages.Livechecked Evidence 1/3WebsiteMCP Registry